#Online Image Annotation using Polygons

[gts6465]

Best Image Annotation Companies Compared: Features, Pricing, and Accuracy

Introduction

As applications powered by artificial intelligence, such as self-driving cars, healthcare diagnostics, and online retail, expand, image annotation has emerged as a crucial component in developing effective machine learning models. However, with numerous providers offering annotation services, how can one select the most suitable Image Annotation Companies for their requirements? In this article, we evaluate several leading image annotation companies in 2025, considering their features, pricing, and accuracy, to assist you in identifying the best match for your project.

1. GTS.AI – Enterprise-Grade Accuracy with Custom Workflows

GTS.AI is renowned for its flexible annotation pipelines, stringent enterprise security standards, and its ability to cater to various sectors such as the automotive, healthcare, and retail industries.

Key Features:

Supports various annotation types including bounding boxes, polygons, keypoints, segmentation, and video annotation.

Offers a scalable workforce that includes human validation.

Integrates seamlessly with major machine learning tools.

Adheres to ISO-compliant data security protocols.

Pricing:

Custom pricing is determined based on the volume of data, type of annotation, and required turnaround time.

Offers competitive rates for datasets requiring high accuracy.

Accuracy:

Achieves over 98% annotation accuracy through a multi-stage quality control process.

Provides annotator training programs and conducts regular audits.

Best for: Companies in need of scalable, highly accurate annotation services across various industries.

2. Labelbox – Platform Flexibility and AI-Assisted Tools

Labelbox provides a robust platform for teams seeking to manage their annotation processes effectively, featuring capabilities that cater to both internal teams and external outsourcing.

Key Features

Include a powerful data labeling user interface and software development kits,

Automation through model-assisted labeling,

Seamless integration with cloud storage and machine learning workflows.

Pricing

Options consist of a freemium tier,

Custom pricing for enterprises,

Pay-per-usage model for annotations.

Accuracy

May vary based on whether annotators are in-house or outsourced, with strong quality

Control tools that necessitate internal supervision.

This platform is ideal for machine learning teams in need of versatile labeling tools and integration possibilities.

3. Scale AI – Enterprise-Level Services for Complex Use Cases

Scale AI is a leading provider in the market for extensive and complex annotation tasks, such as 3D perception, LiDAR, and autonomous vehicle data.

Key Features:

Offers a wide range of annotation types, including 3D sensor data.

Utilizes an API-first platform that integrates with machine learning.

Provides dedicated project managers for large clients.

Pricing

Premium pricing, particularly for high-complexity data.

Offers project-based quotes.

Accuracy:

Renowned for top-tier annotation accuracy.

Implements multi-layered quality checks and human review.

Best for: Projects in autonomous driving, defense, and robotics that require precision and scale.

4. CloudFactory – Human-Centric Approach with Ethical Sourcing

CloudFactory offers a unique blend of skilled human annotators and ethical AI practices, positioning itself as an excellent choice for companies prioritizing fair labor practices and high data quality.

Key Features:

The workforce is trained according to industry-specific guidelines.

It supports annotation for images, videos, audio, and documents.

There's a strong focus on data ethics and the welfare of the workforce.

Pricing

Pricing is based on volume and is moderately priced compared to other providers.

Contracts are transparent.

Accuracy

There are multiple stages of human review.

Continuous training and feedback loops are implemented.

Best for: Companies looking for socially responsible and high-quality annotation services.

5. Appen – Global Crowd with AI Integration

Appen boasts one of the largest international crowds for data annotation, offering extensive support for various AI training data types, such as natural language processing and computer vision.

Key Features

Include a diverse global crowd with multilingual capabilities,

Automated workflows, and data validation tools,

As well as high data throughput suitable for large-scale projects.

Pricing

Appen provides competitive rates for bulk annotation tasks,

With options for pay-as-you-go and contract models.

Accuracy

The quality of data can fluctuate based on project management,

Although the workflows are robust, necessitating a quality control setup.

Best for: This service is ideal for global brands and research teams that need support across multiple languages and domains.

Conclusion: Choosing the Right Partner

The ideal image annotation company for your project is contingent upon your specific requirements:

If you require enterprise-level quality with adaptable services, Globose Technology Solution.AI is recommended.

For those seeking comprehensive control over labeling processes, Labelbox is an excellent choice.

If your project involves intricate 3D or autonomous data, Scale AI is specifically designed for such tasks.

If ethical sourcing and transparency are priorities, CloudFactory should be considered.

For multilingual and scalable teams, Appen may be the right fit.

Prior to selecting a vendor, it is essential to assess your project's scale, data type, necessary accuracy, and compliance requirements. A strategic partner will not only assist in labeling your data but also enhance your entire AI development pipeline.

[macgenceaiml]

The Best Labelbox Alternatives for Data Labeling in 2025

Whether you're training machine learning models, building AI applications, or working on computer vision projects, effective data labeling is critical for success. Labelbox has been a go-to platform for enterprises and teams looking to manage their data labeling workflows efficiently. However, it may not suit everyone’s needs due to high pricing, lack of certain features, or compatibility issues with specific use cases.

If you're exploring alternatives to Labelbox, you're in the right place. This blog dives into the top Labelbox alternatives, highlights the key features to consider when choosing a data labeling platform, and provides insights into which option might work best for your unique requirements.

What Makes a Good Data Labeling Platform?

Before we explore alternatives, let's break down the features that define a reliable data labeling solution. The right platform should help optimize your labeling workflow, save time, and ensure precision in annotations. Here are a few key features you should keep in mind:

Scalability: Can the platform handle the size and complexity of your dataset, whether you're labeling a few hundred samples or millions of images?

Collaboration Tools: Does it offer features that improve collaboration among team members, such as user roles, permissions, or integration options?

Annotation Capabilities: Look for robust annotation tools that support bounding boxes, polygons, keypoints, and semantic segmentation for different data types.

AI-Assisted Labeling: Platforms with auto-labeling capabilities powered by AI can significantly speed up the labeling process while maintaining accuracy.

Integration Flexibility: Can the platform seamlessly integrate with your existing workflows, such as TensorFlow, PyTorch, or custom ML pipelines?

Affordability: Pricing should align with your budget while delivering a strong return on investment.

With these considerations in mind, let's explore the best alternatives to Labelbox, including their strengths and weaknesses.

Top Labelbox Alternatives

1. Macgence

Strengths:

Offers a highly customizable end-to-end solution that caters to specific workflows for data scientists and machine learning engineers.

AI-powered auto-labeling to accelerate labeling tasks.

Proven expertise in handling diverse data types, including images, text, and video annotations.

Seamless integration with popular machine learning frameworks like TensorFlow and PyTorch.

Known for its attention to data security and adherence to compliance standards.

Weaknesses:

May require time for onboarding due to its vast range of features.

Limited online community documentation compared to Labelbox.

Ideal for:

Organizations that value flexibility in their workflows and need an AI-driven platform to handle large-scale, complex datasets efficiently.

2. Supervisely

Strengths:

Strong collaboration tools, making it easy to assign tasks and monitor progress across teams.

Extensive support for complex computer vision projects, including 3D annotation.

A free plan that’s feature-rich enough for small-scale projects.

Intuitive user interface with drag-and-drop functionality for ease of use.

Weaknesses:

Limited scalability for larger datasets unless opting for the higher-tier plans.

Auto-labeling tools are slightly less advanced compared to other platforms.

Ideal for:

Startups and research teams looking for a low-cost option with modern annotation tools and collaboration features.

3. Amazon SageMaker Ground Truth

Strengths:

Fully managed service by AWS, allowing seamless integration with Amazon's cloud ecosystem.

Uses machine learning to create accurate annotations with less manual effort.

Pay-as-you-go pricing, making it cost-effective for teams already on AWS.

Access to a large workforce for outsourcing labeling tasks.

Weaknesses:

Requires expertise in AWS to set up and configure workflows.

Limited to AWS ecosystem, which might pose constraints for non-AWS users.

Ideal for:

Teams deeply embedded in the AWS ecosystem that want an AI-powered labeling workflow with access to a scalable workforce.

4. Appen

Strengths:

Combines advanced annotation tools with a global workforce for large-scale projects.

Offers unmatched accuracy and quality assurance with human-in-the-loop workflows.

Highly customizable solutions tailored to specific enterprise needs.

Weaknesses:

Can be expensive, particularly for smaller organizations or individual users.

Requires external support for integration into custom workflows.

Ideal for:

Enterprises with complex projects that require high accuracy and precision in data labeling.

Use Case Scenarios: Which Platform Fits Best?

For startups with smaller budgets and less complex projects, Supervisely offers an affordable and intuitive entry point.

For enterprises requiring precise accuracy on large-scale datasets, Appen delivers unmatched quality at a premium.

If you're heavily integrated with AWS, SageMaker Ground Truth is a practical, cost-effective choice for your labeling needs.

For tailored workflows and cutting-edge AI-powered tools, Macgence stands out as the most flexible platform for diverse projects.

Finding the Best Labelbox Alternative for Your Needs

Choosing the right data labeling platform depends on your project size, budget, and technical requirements. Start by evaluating your specific use cases—whether you prioritize cost efficiency, advanced AI tools, or integration capabilities.

For those who require a customizable and AI-driven data labeling solution, Macgence emerges as a strong contender to Labelbox, delivering robust capabilities with high scalability. No matter which platform you choose, investing in the right tools will empower your team and set the foundation for successful machine learning outcomes.

Source: - https://technologyzon.com/blogs/436/The-Best-Labelbox-Alternatives-for-Data-Labeling-in-2025

[fromdevcom]

An API (Applications Programming Interface) is a computing interface that dictates the communication and sharing of data between applications. We use APIs in different ways in our day-to-day lives. For example, when you log in to an application using your google account, check the weather on your phone, order food online, or even send an instant message, you are already using an API. You can also use an API to edit images. In addition, if you are building an image editing app, you do not have to build it from scratch. You can implement an API that has the image editing functionalities that you need. That notwithstanding, here are the top image editing APIs for developers; CloudVision API CloudVision API is built by Google for graphic designers and image editing. It can also be used for image recognition. The API comes with features that allow developers to implement image and other object recognition and detection functionalities in their applications. This API can also be used to access data from Google as well as its ML (Machine Learning) libraries. It is these features that make it the best API when it comes to the identification of landmarks and other objects in photos. Developers can also use this API to access picture data in different ways. For instance, you can get things like image descriptions, matching photos, and entity identification. It can also be used to edit images and remove any data that is not needed. Supervise.ly API Supervise.ly API has been used in the development of a web-based tool that is used in editing and formatting videos and images. It can also be used in the annotation media files. This tool can be used by individual academics and big groups of people who want to experiment and annotate with neural networks and datasets. They can use annotation tools such as bitmap brushes, polygons, dots, lines, and boxes, among others. It also comes with support for 3D Point Cloud as well as Data Transformation Language tools. Developers can use this API for things like multi-format data administration and annotation and AI-assisted processing and labeling. Cutout.pro API Cutout.pro API is one of the best APIs especially when it comes to editing images using Artificial Intelligence (AI). Developers can use this API to change picture backgrounds online, remove the background of their videos, retouch and enhance photos, animate and cartoonize photos, make passports from photos, blur photo backgrounds, and colorize images, among others. If you are a developer who wants to incorporate video and image processing powered by AI into your application, then the cutout.pro API is the best bet for you. This functionality can be added to software applications, websites, and other business operations. Imgur API Imgur can be defined as an online community that allows users to share photos and other types of media. Users can share photos that have gone viral on the internet. The platform uses an algorithm to compute and calculate votes, shares, and views. Developers can use the Imgur API with any programming language to access the Imgur platform and implement its functionalities into their applications. For instance, if you want to build a platform similar to Imgur, you just need to implement the API and customize it to meet your requirements. Imgur is a RESTful API, meaning that it accepts HTTP queries. It returns JSON or XML replies. The Imgur API works in the same way as some of the APIs provided by S3 (Amazon), Twitter, and developers can use it for free. You should, however, not use it for commercial purposes. Pixelixe API Pixelixe API offers a photo editing and creation web-based tool that is compatible with all devices, as long as one has a stable internet connection. Its target market is small businesses that want to edit and create images even though they lack design skills. One of the features that make Pixelixe stand out from others is that it allows its users to create and edit photos in bulk.

It also comes with images and templates that allow users to automate their design processes. You can also use its templates if you do not want to create images from scratch. Developers can integrate the Pixelixe API into their applications easily. All they have to do is make sure that they have followed instructions on the API documentation. As a developer, you do not need to spend a lot of time editing images. Additionally, you should not build an image editing tool from scratch when you can implement one of the APIs discussed here.

[callcite-blogs]

Image Annotation Work Online: Essential Skills and Tools for Success in the Digital Age | CallCite

In today’s data-driven world, image annotation has become a crucial component for training machine learning models, particularly in AI-driven applications like computer vision, autonomous driving, and facial recognition. To master this art, working with reliable platforms like Callcite can make all the difference. Here’s how to elevate your image annotation skills and thrive in this growing field.

1. Understanding Image Annotation

Image annotation involves labeling images with metadata to help AI models recognize patterns. It’s the backbone of training datasets that AI systems rely on for tasks like object detection, image segmentation, and classification. Knowing how to apply annotations accurately and consistently is key to success.

2. Key Skills to Develop

To become proficient in image annotation, you must possess attention to detail and a deep understanding of the task at hand. Annotators need to know the specific objects, regions, or features they are marking, and be familiar with various annotation types such as bounding boxes, polygons, and semantic segmentation.

Skills to master:

Label consistency: Ensuring uniform labeling across datasets.

High attention to detail: Minimizing errors that could mislead AI models.

Adaptability: Handling different project requirements and diverse datasets.

3. Tools and Technology

Callcite offers a suite of intuitive, scalable annotation tools designed to handle complex annotation projects with ease. Its AI-driven platform enhances efficiency by automating repetitive tasks, allowing annotators to focus on more intricate labeling needs.

Callcite’s features include:

Easy-to-use interface for manual and automatic annotations.

Support for a wide range of image formats and annotation types.

Seamless collaboration and quality control options.

Conclusion

Mastering image annotation with Callcite ensures that you can contribute to high-quality AI datasets efficiently. By honing essential skills and utilizing top-tier tools, you can thrive in this fast-evolving industry.

[avtechnologysworld]

Comparing the Features of Free AV Design Software

As an audio visual system integrator, designing AV systems and putting together presentations for clients requires software to plan the layout and integrate different elements like video, audio, lighting and more. While paid professional design software provides advanced features, there are also many capable free options available that allow you to create compelling designs without breaking the budget. In this blog post, we will take a look at and compare some of the top free AV design software programs to help you determine which one might be the best tool for your workflow.

QUALITATIVE COMPARISON OF TOP FREE AV DESIGN SOFTWARE

To start, let's qualitatively compare some of the most popular free AV design software in terms of their key features and capabilities. This will give us a high level overview to determine which programs may be worth exploring in more depth.

SweetHome 3D SweetHome 3D is one of the more full-featured free AV design software programs available. It allows you to design floor plans and 3D models of rooms to plan equipment placement. Some key features include:

Floor plan drawing tools to create 2D layouts 3D modeling tools to virtually assemble rooms Large library of furnishings and AV equipment to drag and drop Rendering engine to visualize designs Basic annotation and commenting capabilities Import/export of common file formats Overall it provides a robust set of tools for visualizing AV system designs in 2D and 3D without cost. However, it is more focused on residential rather than commercial applications.

LAVISO Free

As the name implies, LAVISO Free is specifically designed for AV system design. Some highlights are:

Templates for different room types like auditoriums, meeting rooms etc. Comprehensive equipment library with specifications Dimensioning and annotation tools Basic cable routing Bill of materials report generation Option to upgrade to paid professional version While not as full-featured as paid software, LAVISO Free is very capable for basic commercial AV design projects on a tight budget. The interface also has a more professional look compared to general CAD programs.

SketchUp

Being both free and widely used, SketchUp deserves consideration. Some pluses are:

Intuitive 3D modeling interface for laying out spaces Huge 3D warehouse of models to import Dynamic components system for equipment Rendering, section cutting and other views Export to other CAD formats Large online community for help On the downside, it is less focused on AV specifics. Also, Pro and Make versions require payment. But overall SketchUp is very useful as a visualization tool in free form.

AutoCAD/Revit LT

The limited/education versions of AutoCAD and Revit provide many BIM and CAD tools for AV design while remaining free. Benefits include:

Familiar interface for drafting professionals Parametric modeling and interoperability Advanced dimensioning, annotation and sheet layout Library content for structural building elements Export to DXF and other formats However, they lack AV specific components and tools. Complex projects may also hit limits of the free versions. But they enable leveraging existing CAD skills.

DETAILED COMPARISON OF TOP TWO SOFTWARE After this high level overview, let's explore SweetHome 3D and LAVISO Free in more depth by objectively comparing their key features across important criteria. This should help determine which may be the best free option for an audio visual system integrator's specific needs and workflow.

Floor Plan and Space Layout Tools SweetHome 3D has robust 2D floor plan drawing tools including line, rectangle, and polygon drawing modes. Automatic wall connection makes drawing easy. A wide selection of preset rooms, doors and windows are available.

LAVISO Free also provides basic 2D drawing but with greater focus on dedicated AV/control rooms. Templates for standard space layouts streamline starting floor plans. Both import images for tracing existing spaces.

3D Modeling and views SweetHome 3D enables dragging 3D furniture into virtually assembled floor plans from a large database. Dynamic snapping aids placement. Rendering produces photorealistic images and manipulation includes flythroughs.

LAVISO Free does not have true 3D modeling capacities. Equipment is placed on 2D floor plans but bill of quantities reporting considers heights. It focuses more on schematics than photorealistic views.

Equipment Library SweetHome 3D contains a sizable library mostly focused on residential items. Search is basic. User cannot add custom equipment.

LAVISO Free has a more professional commercial AV equipment database with specs downloadable from the manufacturer website. Equipment is parametric and users can define custom components.

Documentation and Reports SweetHome 3D basic dimensioning, annotations and layering. Can place notes, importing images. Rendered scenes and floor plans can be exported.

LAVISO Free enables technical documentation through dimensioning, layering, cable routing annotations and bill of materials/quantities reports. Schematics and specifications exporting supported.

Learning Curve SweetHome 3D is very easy to learn with an intuitive interface for casual users but lacks specialized tools.

LAVISO Free requires more understanding of drawing standards and equipment terminology. Interface is simpler than AutoCAD but more technical than SweetHome 3D. Learning resources are available.

WHICH IS THE BEST FREE AV DESIGN SOFTWARE?

To summarize the detailed comparison, LAVISO Free clearly comes out ahead for an audio visual system integrator's needs:

Focused specifically on AV design with equipment templates More professional library and documentation features Steepest learning curve but aligns with technical nature of work Allows customization and future-proofs projects Free version still capable of basic commercial projects While SweetHome 3D is good for simple residential visualization, LAVISO Free truly enables planning, specifying and communicating commercial AV system designs through its target feature set. The parametric components also future-proof the design if clients want to tweak equipment later.

Of course, no free software matches paid professional options. But for an audio visual integrator on a budget, LAVISO Free delivers the most toolset without restrictions to get the job done capably in 2D. It is highly recommended to evaluate over general purpose programs.

In summary, for free and effective AV design software, LAVISO Free emerges as the top option thanks to its specialized tools and focus on the technical documentation needs of an audio visual system integrator. I hope this detailed comparison has helped you determine the best free software to use in your AV design workflow. Let me know if any other questions!

[teratocrat]

firefox tabs i have open:

tumblr

tumblr notes

one of my mutuals' blog archive4

my own blog archive

five posts ive reblogged

google image search for 'aardwolf'

a tumblr devoted to j.c. leyendecker

a post from 2017 on my old blog about a stand i made (my friend wanted fanstands to try drawing)

five e621 tabs

an ultima iv-v-vi screenshot lp

"morrowind: an oral history" from polygon

online minesweeper site

online solitaire site

wikipedia page for "Aeon"

wikipedia page for "Young's Literal Translation"

wikipedia page for "Chicxulub crater"

wikipedia page for "Axis mundi"

wikipedia page for "Mount Rainier"

itch.io

sword interval

scryfall search "type:dragon"

scrayfall "Ambitious Dragonborn"

mychart login

http://psd.museum.upenn.edu/epsd/e4129.html

google spreadsheet i made to keep track of silly names i made up in case i wanted to name characters in anything

menu for a local teriyaki restaurant

gmail

anime streaming site tabs for Moribito: Guardian of the Spirit, Spirited Away, and Princess Mononoke

cohost

cohost notes

Just King Things episode on The Waste Lands

Just King Things episode on The Tommyknockers

wiktionary page for "audient"

wikipedia page for "Banana"

wikipedia page for "Robert W. Service

wikipedia page for "Li (unit)"

wikipedia page for "Invertebrate iridescent virus 31"

GameFAQs walkthrough and map for Dragon Warrior for the NES

twitter

twitter notes

metropolitan museum of art page on some Qing dynasty agate pomegranates

wikipedia page for "William Howard Taft"

wikipedia page for "Wig"

wikipedia page for "Egyptian cuisine"

google doc where i was trying to transcribe every JKT five-sentence summary

Kill Six Billion Demons KSBD 2-27

Kill Six Billion Demons Breaker of Infinities 4-181

letterboxd

The New Whirling School: An annotated analysis of Sermon 01

youtube subscriptions

youtube Deadmau5 - Ghosts n Stuff

youtube Ranged Touch's 2021 Dark Souls 2 charity livestream part 1

youtube Ranged Touch's 2020 Morrowind charity livestream part 1

youtube Northernlion playing Slice and Dice

youtube Vangelis - Blade Runner Blues

youtube Lady Gaga - Just Dance

youtube Northernlion playing Enter the Gungeon

youtube The Killers - Human

youtube Kanye West - Flashing Lights

manga site for Berserk and Blame!

nine tabs of the Terraria wiki

wikipedia page for "Etruscan civilization"

google search for "forestall"

wikipedia page for "Ran (film)

scryfall search "type:goblin color>=b"

wikipedia page for "Gisella Perl"

wikipedia page for "Overtone singing"

wikipedia page for "Muezzin"

About Us page for Gay City: Seattle's LGBTQ Center

an entirely unused new tab

"An Unknown Kid on Halloween"

uquiz results for "what's your job after the apocalypse"

wikipedia page for "Barnacle goose myth"

wikipedia page for "Vegetable Lamb of Tartary"

rom site

what happens next

youtube William Wegman - Alphabet Soup

events page for a seattle comics & games shop

youtube Ode to Physical Pain

google search for "hyperobject"

prisoncensorship's review of Fallouts 1 & 2

picture i took of the inside of that same comics & games shop

wikipedia page for "Infliximab"

chart showing the evolutionary tree of polearms over time

another mutual's reblogged post

two tabs of the menu of a local pastrami shop

pdf of the third edition monster manual

wikipedia page for "Forgotten Realms"

picture i took of my own backyard covered in snow

scryfall search "set:clb t:dragon is:firstprint"

scryfall search "set"afr t:dragon"

three tabs of file directory for some tabletop pdfs

wikipedia page for "First Blood"

youtube King Missile - Open

someone's website about cat colorations and fur patterns

image a friend sent me of the chapter list of the novel she's writing

Gita Jackson's article comparing Dwarf Fortress and Rimworld

download page for the roguelike "Infra Arcana"

youtube Richard Dawson - Ogre

youtube Every Enemy in Dark Souls RATED - 1 - Undead Asylum

an Exalted 2e homebrew Hegra charmset

a friend's twitter

bilibili video for known Genshin Impact character Xiao

google doc of the rules for a discord server im in

i know i have way too many tabs open please dont yell at me

[ratinglong]

Convert pdf to text in word

#Convert pdf to text in word how to#

#Convert pdf to text in word pdf#

#Convert pdf to text in word pro#

#Convert pdf to text in word pro#

This can be done using our Win2PDF Pro software.

#Convert pdf to text in word pdf#

If you are converting a scanned PDF document, simply upload your PDF as usual. The conversion process will start automatically after the upload is complete. You can upload the PDF directly from your computer, Google Drive, or Dropbox. In order to convert PDF documents using Google Docs, it is necessary to do a few simple manipulations.

#Convert pdf to text in word how to#

And there’s an easy solution for this as well. How to convert PDF to Word free online: Upload your file to our free online PDF to Word converter. Now, what if you don’t want your PDF files converted to Word, or modified in any way?įor that, you just need to encrypt the PDF file to prevent modifications. Currently, Google’s conversion process does seem somewhat limited and some formatting may be lost, but it will give you an editable Word document from the original PDF file. Tap on files from this device to upload PDF from your mobile. Choose the location where your PDF file is stored. Convert PDF to Word directly from the app: 1. Download the file as a Microsoft Word (.docx) formatted fileĪnd that’s it. There are two ways to use this file converter to convert PDF files to Word: by starting the app or opening a PDF file in a PDF viewer. And once it is a Google Doc, it can be saved as another format, including Microsoft Word.ģ. When you open with Google Docs, the PDF file will be converted to a Google doc. Right-mouse click on the PDF file in Google Drive, and open the file in Google Docs Then, choose the PDF file on your hard drive that you wish to convert to a Microsoft Word document.Ģ. Once Google Drive is open, choose Upload files… from the My Drive drop-down menu. This will allow you to open another Google app associated with your account, including Google Drive. Here are the basic steps:įrom a Gmail account or any other Google app, click on the Google Apps icon. One of the easiest methods is to use Google Docs to do the conversion from PDF to Word. While there are some specialized commercial programs that do this conversion, there are also free alternatives available.

Other features like create, print, share, redact, flatten PDF files.This article about Paul Manafort made the headlines the other day, and it got us wondering: How many people know how to convert a PDF file to a Microsoft Word document? Do you?.

Extract text from images and transfer scanned documents into editable with OCR.

Optimize PDF and reduce the file size of PDF documents.

Convert PDF files to different formats, including Office formats, RTF, HTML, and Epub.

Add different shapes including oval, line, arrow, rectangle, and polygon shapes.

Add sticky notes and text boxes to annotate and markup files.

Add text, image, or link to the PDF File.

Edit text and images in the PDF document.

When the document is uploaded, you can click 'Convert'. Wait a few moments for the website to upload the document. Or, click on 'Choose File' and locate the file on your computer. Drag and drop the file you want to convert. With that in mind, here are some unique features. Choose the 'PDF to Word' option on the main page. Unlike other full-featured software options, PDFelement is affordable. For example, when you click on "Convert", you will open options for different formats, but also for OCR and Optimize PDF. Clicking on any section will open new features. Features are divided into main categories. With an intuitive design, you can easily find everything you need. Simplicity is one of the main focus of the interface. To begin with, the software is simple to use. There are a couple of reasons why PDFelement stands out of the crowd. As you can see, batch converting documents is easy with PDFelement.

[mmorgslim]

Drawboard pdf surface pro 4

#Drawboard pdf surface pro 4 pdf

#Drawboard pdf surface pro 4 windows 10

#Drawboard pdf surface pro 4 android

#Drawboard pdf surface pro 4 free

Windows, Mac, GNU/Linux) Inkscape can help.

#Drawboard pdf surface pro 4 free

Need a vector graphics editor? Read this blog entry, Vector Images: Make Magic with Two Free Tools, to see how cross-platform (e.g.

#Drawboard pdf surface pro 4 pdf

In a pinch, you can skip buying the expensive Adobe Pro software to edit a PDF document. Here’s a video walking you through the process of PDF editing with Inkscape: It only allows you to edit a single page at a time and insert images onto a page in a PDF. Need to edit words on a page in PDF? If you need to change the words on the page, then Inkscape will get the job done. Want to merge, re-order, or arrange PDF documents? You will need to get the Pro version of Drawboard PDF ( $4.99 on sale or $9.99 regular price). You can even insert dynamic content like ink signatures, images, text boxes, and notes. You have maximum control over your digital pens and markers.ĭrawboard make inserting editable shapes, lines, arrows, polygons and clouds straightforward. While Drawboard isn’t the simplest to use (I find the radial interface confusing), some will like how easy it is to highlight the screen and annotate it.

Ink annotations feel just like pen and paper.

Drawboard boasts various features, such as the following:

#Drawboard pdf surface pro 4 windows 10

The first time I tried Drawboard PDF on my Windows 10 tablet, I almost threw the tablet out the window.

#Drawboard pdf surface pro 4 android

Windows, iOS, Android devices Mac and Chromebook via the Web) you are on. This is a great, free tool to use, no matter what device (e.g. On their website, you’ll find testimonials from its users, including classroom teachers.

Secure: your files never leave your computer.

Organize pages: insert, delete, reorder, and rotate pages (NEW!).

Each link points to an illustrated blog post: You can now insert, delete, reorder, and even rotate pages to manipulate your PDF to fit your needs…Xodo can also open other file formats such as docx, pptx, jpeg, png, cbz, and other image files. The new Xodo web app provides more flexibility than ever before. And now you can merge PDFs from your computer and Google Drive. With the Xodo web app, you can now merge multiple PDFs into one, which is perfect for when you need to compile resources into one package to send to your colleagues. A little more information about Xodo is available online: In addition to working as a native app on your Android or Windows 10 device, you can also access it via a web browser. Sure enough, you can get Xodo as an app in the Windows 10 Store. After using Xodo to get the PDF on its way, I made a mental note to see if it was available on Windows 10. My Windows 10 device was stowed away the only device I had was my Android phone. I had to fill out a PDF form, sign it, and then email it. When I found Xodo, I was waiting to board a plane. Let’s take a look at some of my favorites. Now that you know what I’m looking for in a PDF editor. Therefore, you won’t find FoxIt, Adobe, or NitroPDF on this list. We all need a little less complexity in our lives. But one reason to keep it simple is that Adobe Acrobat Pro offers so many features that they are baffling. These four criteria do not include everything you could look for in a PDF editor.

It’s easy to split PDF files into their individual pages or combine multiple pages/PDF files into one.

The program facilitates editing, filling out forms, and signing documents.

Here are my criteria for simple PDF tools: Some feature complex graphical user interfaces (GUIs). With PDF annotation tools, you have many to choose from. The main thing I am looking for is simple tools that get the job done. Get infographic as a Google Slides template you can use PDF Criteria

[vplong]

Geometry sketchpad activities

#Geometry sketchpad activities update

#Geometry sketchpad activities code

#Geometry sketchpad activities tv

#Geometry sketchpad activities free

Export to several file formats and destinations, including vector PDFs and AirPrint.

Isosceles automatically stores your sketches in iCloud so your documents are available across all your devices.

This allows you to take advantage of the seamless LaTeX rendering without the hassle of learning to write TikZ code.

#Geometry sketchpad activities code

LaTeX users: Create your geometric figures in Isosceles and import them as TikZ code into your LaTeX documents.Take advantage of the simple yet versatile export options for sharing sketches with colleagues.The isometric grid snaps figures as you draw, making 3D schematics easy.Isosceles's smart snapping system takes care of neatness, letting you focus on making your clients happy with great designs.Solve construction problems and multiple choice questions after each tutorial to get the best preparation for geometry tests and the ACT/SAT.Isosceles gives you access to 16 geometry activities and over 50 practice questions in 4 categories: Intro to Geometry, Lines, Circles, and Triangles.The handy notes sidebar accessible with a single tap makes taking notes in geometry effortless.Add marks to show congruency and parallel objects, extend lines, show live measurements, and more.View and edit information about any object, such as the length of a line or the circumference of a circle.Put together homework assignments quickly by constructing diagrams with Isosceles.

#Geometry sketchpad activities tv

Connect your iPad to a TV or projector to present class material or demonstrate a construction.

Switch between four distinct templates (Classical, Cartesian, Isometric, and Polar) to fit any kind of drawing.

Insert images and graph functions directly in your sketches.

Write or draw freeform on the canvas in addition to drawing geometric shapes.

#Geometry sketchpad activities update

Create smart text annotations that update their value based on the figures and calculations you type.

Add text annotations and mathematical expressions anywhere in the drawing.

Features like double/triple lines and point styles open up new uses for Isosceles, such as drawing chemical diagrams or graphs.

Isosceles automatically snaps new additions to nearby objects, keeping your drawing accurate so you can focus on the construction.

The simple, versatile drawing tools (lines, circles, arcs, polygons, and conics) can be combined to create complex drawings.

They dilate and then translate a point, restrict these points to number lines, and ultimately observe that in the algebraic equation y = mx + b, m corresponds to the scale factor for dilation and b corresponds to the length of the vector for translation.Isosceles is the perfect geometry drawing tool for students, teachers, and professionals. In particular, students work with geometric transformations as functions that take an input point and produce an output point, and relate these functions to algebra by using them to construct the Cartesian graph of a generalized linear function. Our article summarizes our curriculum unit, Connecting Geometry and Algebra Through Functions. This unit’s Web-Sketchpad-based activities connect functions in geometry (transformations whose variables are points on the plane) with functions in algebra (whose variables are points on the number line). All of the figures were built with Web Sketchpad.

#Geometry sketchpad activities free

News alert! Scott and I wrote the cover story, Connecting Functions in Geometry and Algebra, in this month’s Mathematics Teacher. You can read the article in print, but better yet, go to the free online version. This is the first time Mathematics Teacher has incorporated live dynamic-mathematics figures into its online offerings, allowing readers to manipulate the mathematical objects in those figures as they read.

[furioussandwichstrawberry]

Adobe Reader For Pc

Jul 17, 2019.

Download Adobe Reader For Laptop

Adobe Reader For Pc Free Download

Adobe Reader For Pc Free

Business professionals use Adobe PDFs for countless document types. Personal uses abound as well and could include summer camp forms, job applications, mortgage and home ownership documentation, legal contracts, medical records, etc. People trust and use this file type because a PDF carries a level of professional credibility. The frequency of which people interact with PDFs is the best reason to have an Adobe-specific app. Adobe Reader DC is a free app for Windows, giving you the ability to work with PDFs anywhere, anytime.

What are the capabilities of Adobe Acrobat Reader DC?

There’s no wonder Adobe Reader DC is installed on over 600 million devices

Adobe is changing the world through digital experiences. We help our customers create, deliver and optimize content and applications. Video editing that’s always a cut above. Create amazing videos with the power of Premiere Pro and the portability of Premiere Rush. Start free trial. Adobe Reader DC works seamlessly with other Adobe apps such as Adobe Scan, where users can scan important documents, and work on them within Adobe Reader.

With the Adobe Reader DC app, users can open and view PDF documents quickly, search within the document for specific verbiage, scroll through the document, and zoom in and out. Users can interact with the PDF as well by comment directly on the document using drawing tools or sticky notes, highlight text, and view and reply to other comments within the PDF. You can even receive notifications for files you have personally shared or documents shared with you which contain pending actions. Reviewing and signing a PDF has never been easier with Adobe Reader DC’s signature capability. Once you are ready to share your PDF, simply create a customized link and send via email, or collaborate directly within the app.

Adobe Reader DC works seamlessly with other Adobe apps such as Adobe Scan, where users can scan important documents, and work on them within Adobe Reader DC. Within the Reader app, users can view their PDFs in three different modes: fit to screen, continuous scroll, and reflow.

It’s important to note that the Adobe Reader DC app for Windows, while convenient and free, has limited PDF capabilities. The ability to edit fields, format documents, etc. is only available with an upgrade to Adobe Acrobat Pro DC. The basic Reader DC app is free, with in-app purchases available, including Acrobat Pro DC.

The app is fast, easy to navigate, and makes viewing and annotating PDFs on-the-go much easier. The interface itself is well organized and clean in appearance. The download is very fast, getting Windows users up to speed in no time.

Adobe’s Privacy Policy is similar to that of other large tech companies. Adobe uses personal information to provide users with specialized, targeted websites, apps, and other products or services. They use cookies to track the use of their website and apps. Adobe shares personal information within the Adobe family, outside advertising and sales companies, and third-party companies. Overall, Adobe is a reputable and trustworthy company, with policies in line with industry standards. Users can feel confident downloading and using Adobe products.

No hardware configuration – reduced hassle of fast downloadsThe new BitTorrent 7 brings together BitTorrent’s proven expertise in networking protocols with µTorrent’s efficient implementation and compelling UI to create a better BitTorrent client. As we continue to develop this new client, we’ll be focused on innovative ways to simplify and improve the BitTorrent user experience. Detailed stats on the health of media files provides a safer, more controlled experience. https://furioussandwichstrawberry.tumblr.com/post/643835308024201216/bittorrent-portable.

Where can you run this program?

Adobe Reader DC is available on Windows, macOS, Android, iOS and Windows Phone devices. Reader is a 71.24 MB download. It is available in over 25 languages.

Is there a better alternative?

There are many app alternatives for users with PDF needs. While Acrobat Reader DC is the most common software for this need, other options include Foxit PDF Reader and Nitro PDF.

Our take

If you ever find yourself needing to open, view, sign, or share a PDF, the Acrobat Reader DC app for Windows is the way to go. Being of the publisher Adobe itself, it is optimized to open and navigate your important PDFs with ease. Download this app if you need to access PDF documents from your PC.

Should you download it?

Yes, absolutely! It's a must-have for the average Windows user.

2019.012.20034

Adobe Acrobat Pro DC Crack & License Key 2020.012.20043 [Working]

Adobe Acrobat Pro DC Crack is the standard program for professional use of PDF files. With just a few mouse clicks, you can produce PDF files of documents, images, and many other types of files that can be opened with a PDF reader. It also includes the most important functions for viewing, printing, signing, and commenting PDF files, and it is the only accessible PDF viewer that will be able to open and connect with all kinds of PDF content materials, including multimedia and forms. Also, Adobe Acrobat Pro DC keygen 2020.12.20043 k full download is useful for both teachers and college students while learning, writing some thesis or doing homework, and much more if we need a book or a quote from the web.

Free download support for Adobe Acrobat Pro DC Patch for Adobe Flash indicates that feature-rich interactive documents can be very good, and audio and video types, for example, MP3 and QuickTime can also be included in PDF files. PDF forms can be viewed, completed, saved, and tagged with this tool (if the registrar gives you the required rights). In addition to smooth reading, the viewer provides a set of editing tools. Among other activities, you can cross out paragraphs of textual content, emphasize areas with a marker, place sticky notes, and draw lines, arrows, or paint and polygons with a pen.

With the full version of Adobe Acrobat Pro DC Activation Code, you can control document reviews, generate opinions from multiple reviewers while maintaining the format and integrity of the record. Therefore, it extends the commenting functions to anyone who uses this complete program. In addition, Windows Home users can design intelligent Adobe PDF forms that consist of business logic, such as calculations and data validation, to help increase the accuracy of data collection and reduce costs for standard data access. Also, digital signatures can be combined and scanned.

https://furioussandwichstrawberry.tumblr.com/post/643835384147640320/mac-up-date. Jul 31, 2020.

Adobe Acrobat Pro DC Cracked generates a high-quality result. By extracting something from PDF data files, you don’t need to worry about quality. Generally does not change the rating of PDF content. In general, it does not harm your privacy and confidentiality, since it protects all your documents with high priority.

Therefore, Adobe Acrobat is fully compatible with almost all texture formats. Therefore, there must be a special program to help you read all text formats. Adobe Acrobat Pro DC Serial Number Generator is the best program that supports all writing formats and exposes you with its realistic appearance and style. You can also create a text file for your business in an easy way.

You may also download: Adobe Premiere Pro 2020 Crack v14.3.1.45

Key features of Adobe Acrobat Pro DC:

Attractive, smart, and easy to use interface.

You have a complete privacy protection package for your documents.

After creating a document, it provides you with proof of the image so you can share it with anyone else.

Plus, it has an electronic signature feature that’s great.

An automatic file detection system that makes its use easier and innovative.

Download many books with one click.

An easy file comparison tool.

Works best on Mac.

Ultra-powerful document scanning system.

Its portable version also includes the necessary document editing tools.

Desktop, new user support for VMware Horizon.

Millions of professionals choose.

Very easy to use.

The latest and only rich text styles.

Multi-language support.

Online customer service.

Easy to use program.

Very simple and easy to use.

And much more …

What’s new in Adobe Acrobat Pro?

The latest version comes with several bugs that fix specific functionality issues in this version of Adobe Acrobat Pro DC (20.006.20034).

Addresses an issue in Acrobat Pro DC where it won’t shut down and consumes CPU if registry mapping is not present on the system.

There is no longer an issue that you were unable to fill out certain PDF forms created in LiveCycle Designer.

The error that creates a problem when the Zoom tool appears gray when opening a PDF in the SAP GUI is no longer.

The issue was also resolved when opening a PDF in Acrobat / Reader from any untitled PDF URL.

Fixed an issue that a user could not print to Adobe PDF from Safari.

Many other improvements and updates.

Necessary system requirements of Adobe Acrobat Pro DC Cracked:

Windows XP / Vista all versions.

Windows 7,8,8.1 and 10 (32-64 bit).

Mac OS X 10 or 10.6 or later.

I am an explorer 10 or higher.

2 GHz Pentium 4 processor.

1 GB of RAM.

500 MB of hard disk space is enough.

1024 x 768 screen.

New License Keys for Adobe Acrobat Pro DC:

NGJLCIDOS73DZRO6GE08ZETY3

NJVG6-CFXR3-IKBR1-4ZE7BF-H5VFI

676T6-9OLKJ-MHTYU-I8O90-PO5TM Ocr download freeware.

BHFYX-TGXE4-MHFQ9-KVYX4Z-TDHXP

HBGCF-YFRSX-UNVFE-VGDIV-EXAFX

NVFS3-TXCE2-BHGUI-LIVDE-XDRFI

Serial key: BGAI8-TAV5F-KIAB4-DF82V-DEX9L

Serial number: JAH6T-567IK-JHGFE-RT56Y-U7IKG

Activation key: FR67I-8JHGR-5467U-YT566-7ITR4

Product Key: 567ET-R456Z-SW345-678IU-JHTR5:

License key: GTY67-67U8I-K78I7-78567-IUTYY

Pros:

Adobe Acrobat is a widely used PDF reader in the world.

The app contains advanced features and increased support.

Clear and fast adjustments.

Cons:

There is no flaw that can explain.

How to Crack Adobe Acrobat Pro DC 2020?

Get the latest trial version on your device and install it.

Run it.

Get your Crack incl License now from the link here.

Save it and play.

Wait a few seconds.

Then restart Adobe Acrobat Pro DC and enjoy all the features for free.

This facility is for students only.

Download Adobe Reader For Laptop

Adobe Acrobat Pro DC 2020.12.20048 Crack + Serial Key full. free download

Adobe Reader For Pc Free Download

Adobe Acrobat Pro DC 2020.12.20048 Crack + Serial Key full. free download: is the standard program for professional use of PDF files. With just a few mouse clicks, you can produce PDF files of documents, images

Operating System: Windows 7,8,8.1,10

Adobe Reader For Pc Free

Application Category: Software

[hafizhamza313]

The best free PDF editor 2019: edit documents without paying a penny

The best free PDF editor 2019: edit documents without paying a penny

Truly great free PDF editors are hard to come by, but there are some excellent tools around if you know where to look. PDF documents are designed to look and behave exactly the same way on any device. That makes it a brilliant format for sharing, but editing them is another matter. Most office software and photo editors let you export documents in PDF format, but editing requires a dedicated tool. That's because PDF was initially a proprietary format owned by Adobe, and it still owns some of the technologies associated with it. Other companies can license those technologies, but only for a fee that's usually passed on to you – the user. There aren’t many free PDF editors and even fewer that won’t leave your documents with unsightly watermarks. That's why we've rounded up the very best free PDF editing software that's free to use and won't add any unwanted extras to your work.  

You won't find a more flexible free PDF editor than ApowerPDF (Image credit: Apowersoft)   There are two options on the ApowerPDF homepage: ‘Launch Online’ and ‘Download Desktop’. Despite appearances, these aren’t the same tools. The desktop software is only a trial of a premium product and will watermark your edited PDFs. The tool we’re using here is the online editor, which has no such limitations. Click ‘Launch Online’ and you’ll be prompted to download and run a small launcher app, after which the online editor will launch. You can edit text (including formatting), add text and images, encrypt documents with a password, convert your PDF to an image file and add comments. You can even create your own PDFs from scratch – a feature you’ll usually only find in premium PDF editing software. Unlike the desktop application, there’s no tool for removing watermarks from PDFs, but that’s a minor quibble. ApowerPDF is a remarkable PDF editor; just make sure you’re using the online edition. If you would prefer the desktop version, Apower PDF costs from $29.95 (£25) after the free trial period. Try ApowerPDF online  

Unlike many free PDF editors, PDF-XChange editor lets you delve in and make changes to the text (Image credit: Tracker Software)   If you need to edit the text in a PDF, PDF-XChange Editor is ideal. It lets you retype, delete, and reformat text, and adapts well if the document uses a font that isn’t installed on your PC. You can also attach comments, split PDFs, and extract pages. One of PDF-Xchange Editor’s best features is the ability to use OCR to recognize text in scanned documents – ideal if you only have a printout rather than the original file (a handout from a lecture, for example). Some of the features visible in the menus and toolbars are only available in the premium version of the software, PDF-XChange Editor Plus, but you can easily hover your mouse pointer over an icon to find out if it’s included. If you go ahead and use a premium tool anyway (adding polygonal shapes or new text boxes, for example), your document will be watermarked. Look out for a warning message underneath the main toolbar before saving your work, just in case. The paid-for downloads, PDF-XChange Editor costs $43.50 (£35) for the normal version, but for additional features such as form creation and use you will need to buy PDF-XChange Editor Plus, which costs $54.50 ($48). Download PDF-XChange Editor  

If you have a reliable internet connection, give Sedja a try and edit PDFs in your web browser (Image credit: Sedja BV)   Free online PDF editor Sedja offers an excellent range of tools, with just one caveat: if you're still working after three hours and haven't saved your document, it will be deleted automatically. It's quite a generous time limit, but worth bearing in mind if your PDF needs a lot of work. You can add text, images and links, sign documents, add annotations, and insert ellipses and rectangles. There’s also a ‘whiteout’ option, though this simply draws a white rectangle – it doesn’t remove any data. There’s no OCR either, so you won’t be able to edit the text in scanned PDFs. When you’ve finished editing, click ‘Apply changes’ and you’ll be able to download the document, send it to Dropbox or Google Drive, delete it, or access a shareable link. The link will expire after seven days. There is a free version, available to download or use in the cloud, which has limited features. To open these up you will need to pay for a paid plan. The Web Week Pass is aimed at short-term use and costs $5 (£4) to access the web-based version for 7 days. If you'd prefer to pay on a monthly recurring basis, then the cloud version is $7.50 (£6) per month. A desktop version is available to download and use, which also allows web access, and that costs $63 annually, which works out as the equivalent of $5.25 per month. You can download Sedja here  

It looks a little old-school, but PDFescape offers an impressive selection of editing tools (Image credit: Red Software)   There are two versions of PDFescape: a free web app and a premium desktop program. Here we're using the online editor; if you download the desktop software, you'll only receive a trial of the premium edition. PDFescape's online editor lets you create new text boxes on the page, but unfortunately, there's no way to edit existing text. You can create simple geometric shapes and– as with Sedja, above – add white rectangles to obscure parts of the document when it's printed. PDFescape lets you select a picture from your PC, then drag a rectangle to insert it. You can insert text fields too, enabling you to create simple forms – a rare and welcome feature for a free PDF editor. While the online editor is free for editing, creating forms, and sharing, there are also two paid-for versions available. The Premium version is for desktop and includes print to scan, and is available for $2.99 (£2.50) per month. The Ultimate version costs $5.99 per month and comes with more advanced features, such as publishing PDF forms. Try PDFescape  

For simply splitting and merging PDFs, PSFsam is all you need (Image credit: Sober Lemur)   The latter half of PDFsam’s name is short for ‘split and merge’, which tells you pretty much everything you need to know about the Basic edition. You’ll be offered a free trial of the premium version (including full editing, object insertion, secure signing, and OCR), but once that expires you’ll be left with a simple but well-designed tool for chopping large documents into manageable chunks, performing a PDF cut-and-shut, or extracting selected pages. You can also use PDFsam Basic to rotate pages, which is very handy if you’ve accidentally scanned a document upside down. There are no tools for tweaking the actual content of the document, but all of PDFsam Basic’s page-management options are very clearly laid out, and it’s very clear which of the options shown in the main menu are only available in the premium edition. However, if you'd prefer the advanced features of PDFsam Enhanced, there are 3 different plans available, costing $39 ($34), $49 (£44), or $69 (£60) a year, depending on the range of extra features required. Download PDFsam Basic Read the full article

[smartecky]

Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but lidar has proven transformative. The latest accomplishment using laser-based imaging maps thousands of square kilometers of an ancient Mayan city once millions strong, but the researchers make it clear that there’s no technological substitute for experience and a good eye.

The Pacunam Lidar Initiative began two years ago, bringing together a group of scholars and local authorities to undertake the largest-yet survey of a protected and long-studied region in Guatemala. Some 2,144 square kilometers of the Maya Biosphere Reserve in Petén were scanned, inclusive of and around areas known to be settled, developed or otherwise of importance.

Preliminary imagery and data illustrating the success of the project were announced earlier this year, but the researchers have now performed their actual analyses on the data, and the resulting paper summarizing their wide-ranging results has been published in the journal Science.

The areas covered by the initiative, as you can see, spread over perhaps a fifth of the country.

“We’ve never been able to see an ancient landscape at this scale all at once. We’ve never had a data set like this. But in February really we hadn’t done any analysis, really, in a quantitative sense,” co-author Francisco Estrada-Belli, of Tulane University, told me. He worked on the project with numerous others, including Tulane colleague Marcello Canuto. “Basically we announced we had found a huge urban sprawl, that we had found agricultural features on a grand scale. After another nine months of work we were able to quantify all that and to get some numerical confirmations for the impressions we’d gotten.”

“It’s nice to be able to confirm all our claims,” he said. “They may have seemed exaggerated to some.”

The lidar data was collected not by self-driving cars, which seem to be the only vehicles bearing lidar we ever hear about, nor even by drones, but by traditional airplane. That may sound cumbersome, but the distances and landscapes involved permitted nothing else.

“A drone would never have worked — it could never have covered that area,” Estrada-Belli explained. “In our case it was actually a twin-engine plane flown down from Texas.”

The plane made dozens of passes over a given area, a chosen “polygon” perhaps 30 kilometers long and 20 wide. Mounted underneath was “a Teledyne Optech Titan MultiWave multichannel, multi-spectral, narrow-pulse width lidar system,” which pretty much says it all: this is a heavy-duty instrument, the size of a refrigerator. But you need that kind of system to pierce the canopy and image the underlying landscape.

The many overlapping passes were then collated and calibrated into a single digital landscape of remarkable detail.

“It identified features that I had walked over — a hundred times!” he laughed. “Like a major causeway, I walked over it, but it was so subtle, and it was covered by huge vegetation, underbrush, trees, you know, jungle — I’m sure that in another 20 years I wouldn’t have noticed it.”

But these structures don’t identify themselves. There’s no computer labeling system that looks at the 3D model and says, “this is a pyramid, this is a wall,” and so on. That’s a job that only archaeologists can do.

“It actually begins with manipulating the surface data,” Estrada-Belli said. “We get these surface models of the natural landscape; each pixel in the image is basically the elevation. Then we do a series of filters to simulate light being projected on it from various angles to enhance the relief, and we combine these visualizations with transparencies and different ways of sharpening or enhancing them. After all this process, basically looking at the computer screen for a long time, then we can start digitizing it.”

“The first step is to visually identify features. Of course, pyramids are easy, but there are subtler features that, even once you identify them, it’s hard to figure out what they are.”

The lidar imagery revealed, for example, lots of low linear features that could be man-made or natural. It’s not always easy to tell the difference, but context and existing scholarship fill in the gaps.

“Then we proceeded to digitize all these features… there were 61,000 structures, and everything had to be done manually,” Estrada-Belli said — in case you were wondering why it took nine months. “There’s really no automation because the digitizing has to be done based on experience. We looked into AI, and we hope that maybe in the near future we’ll be able to apply that, but for now an experienced archaeologist’s eye can discern the features better than a computer.”

You can see the density of the annotations on the maps. It should be noted that many of these features had by this point been verified by field expeditions. By consulting existing maps and getting ground truth in person, they had made sure that these weren’t phantom structures or wishful thinking. “We’re confident that they’re all there,” he told me.

“Next is the quantitative step,” he continued. “You measure the length and the areas and you put it all together, and you start analyzing them like you’d analyze other data set: the structure density of some area, the size of urban sprawl or agricultural fields. Finally we even figured a way to quantify the potential production of agriculture.”

This is the point where the imagery starts to go from point cloud to academic study. After all, it’s well known that the Maya had a large city in this area; it’s been intensely studied for decades. But the Pacunam (which stands for Patrimonio Cultural y Natural Maya) study was meant to advance beyond the traditional methods employed previously.

“It’s a huge data set. It’s a huge cross-section of the Maya lowlands,” Estrada-Belli said. “Big data is the buzzword now, right? You truly can see things that you would never see if you only looked at one site at a time. We could never have put together these grand patterns without lidar.”

“For example, in my area, I was able to map 47 square kilometers over the course of 15 years,” he said, slightly wistfully. “And in two weeks the lidar produced 308 square kilometers, to a level of detail that I could never match.”

As a result the paper includes all kinds of new theories and conclusions, from population and economy estimates, to cultural and engineering knowledge, to the timing and nature of conflicts with neighbors.

The resulting report doesn’t just advance the knowledge of Mayan culture and technology, but the science of archaeology itself. It’s iterative, of course, like everything else — Estrada-Belli noted that they were inspired by work done by colleagues in Belize and Cambodia; their contribution, however, exemplifies new approaches to handling large areas and large data sets.

The more experiments and field work, the more established these methods will become, and the greater they will be accepted and replicated. Already they have proven themselves invaluable, and this study is perhaps the best example of lidar’s potential in the field.

WTF is lidar?

“We simply would not have seen these massive fortifications. Even on the ground, many of their details remain unclear. Lidar makes most human-made features clear, coherent, understandable,” explained co-author Stephen Houston, of Brown University, in an email. “AI and pattern recognition may help to refine the detection of features, and drones may, we hope, bring down the cost of this technology.”

“These technologies are important not only for discovery, but also for conservation,” pointed out co-author, Ithaca College’s Thomas Garrison, in an email. “3D scanning of monuments and artifacts provide detailed records and also allow for the creation of replicas via 3D printing.”

Lidar imagery can also show the extent of looting, he wrote, and help cultural authorities provide against it by being aware of relics and sites before the looters are.

The researchers are already planning a second, even larger set of flyovers, founded on the success of the first experiment. Perhaps by the time the initial physical work is done the trendier tools of the last few years will make themselves applicable.

“I doubt the airplanes are going to get less expensive but the instruments will be more powerful,” Estrada-Belli suggested. “The other line is the development of artificial intelligence that can speed up the project; at least it can rule out areas, so we don’t waste any time, and we can zero in on the areas with the greatest potential.”

He’s also excited by the idea of putting the data online so citizen archaeologists can help pore over it. “Maybe they don’t have the same experience we do, but like artificial intelligence they can certainly generate a lot of good data in a short time,” he said.

But as his colleagues point out, even years in this line of work are necessarily preliminary.

“We have to emphasize: it’s a first step, leading to innumerable ideas to test. Dozens of doctoral dissertations,” wrote Houston. “Yet there must always be excavation to look under the surface and to extract clear dates from the ruins.”

“Like many disciplines in the social sciences and humanities, archaeology is embracing digital technologies. Lidar is just one example,” wrote Garrison. “At the same time, we need to be conscious of issues in digital archiving (particularly the problem of obsolete file formatting) and be sure to use technology as a complement to, and not a replacement for methods of documentation that have proven tried and true for over a century.”

The researchers’ paper was published today in Science; you can learn about their conclusions (which are of more interest to the archaeologists and anthropologists among our readers) there, and follow other work being undertaken by the Fundación Pacunam at its website.

Read more: https://techcrunch.com/2018/09/27/how-aerial-lidar-illuminated-a-mayan-megalopolis/

How aerial lidar illuminated a Mayan megalopolis Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but…

[peach5200-blog]

Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but lidar has proven transformative. The latest accomplishment using laser-based imaging maps thousands of square kilometers of an ancient Mayan city once millions strong, but the researchers make it clear that there’s no technological substitute for experience and a good eye.

The Pacunam Lidar Initiative began two years ago, bringing together a group of scholars and local authorities to undertake the largest-yet survey of a protected and long-studied region in Guatemala. Some 2,144 square kilometers of the Maya Biosphere Reserve in Petén were scanned, inclusive of and around areas known to be settled, developed or otherwise of importance.

Preliminary imagery and data illustrating the success of the project were announced earlier this year, but the researchers have now performed their actual analyses on the data, and the resulting paper summarizing their wide-ranging results has been published in the journal Science.

The areas covered by the initiative, as you can see, spread over perhaps a fifth of the country.

“We’ve never been able to see an ancient landscape at this scale all at once. We’ve never had a data set like this. But in February really we hadn’t done any analysis, really, in a quantitative sense,” co-author Francisco Estrada-Belli, of Tulane University, told me. He worked on the project with numerous others, including Tulane colleague Marcello Canuto. “Basically we announced we had found a huge urban sprawl, that we had found agricultural features on a grand scale. After another nine months of work we were able to quantify all that and to get some numerical confirmations for the impressions we’d gotten.”

“It’s nice to be able to confirm all our claims,” he said. “They may have seemed exaggerated to some.”

The lidar data was collected not by self-driving cars, which seem to be the only vehicles bearing lidar we ever hear about, nor even by drones, but by traditional airplane. That may sound cumbersome, but the distances and landscapes involved permitted nothing else.

“A drone would never have worked — it could never have covered that area,” Estrada-Belli explained. “In our case it was actually a twin-engine plane flown down from Texas.”

The plane made dozens of passes over a given area, a chosen “polygon” perhaps 30 kilometers long and 20 wide. Mounted underneath was “a Teledyne Optech Titan MultiWave multichannel, multi-spectral, narrow-pulse width lidar system,” which pretty much says it all: this is a heavy-duty instrument, the size of a refrigerator. But you need that kind of system to pierce the canopy and image the underlying landscape.

The many overlapping passes were then collated and calibrated into a single digital landscape of remarkable detail.

“It identified features that I had walked over — a hundred times!” he laughed. “Like a major causeway, I walked over it, but it was so subtle, and it was covered by huge vegetation, underbrush, trees, you know, jungle — I’m sure that in another 20 years I wouldn’t have noticed it.”

But these structures don’t identify themselves. There’s no computer labeling system that looks at the 3D model and says, “this is a pyramid, this is a wall,” and so on. That’s a job that only archaeologists can do.

“It actually begins with manipulating the surface data,” Estrada-Belli said. “We get these surface models of the natural landscape; each pixel in the image is basically the elevation. Then we do a series of filters to simulate light being projected on it from various angles to enhance the relief, and we combine these visualizations with transparencies and different ways of sharpening or enhancing them. After all this process, basically looking at the computer screen for a long time, then we can start digitizing it.”

“The first step is to visually identify features. Of course, pyramids are easy, but there are subtler features that, even once you identify them, it’s hard to figure out what they are.”

The lidar imagery revealed, for example, lots of low linear features that could be man-made or natural. It’s not always easy to tell the difference, but context and existing scholarship fill in the gaps.

“Then we proceeded to digitize all these features… there were 61,000 structures, and everything had to be done manually,” Estrada-Belli said — in case you were wondering why it took nine months. “There’s really no automation because the digitizing has to be done based on experience. We looked into AI, and we hope that maybe in the near future we’ll be able to apply that, but for now an experienced archaeologist’s eye can discern the features better than a computer.”

You can see the density of the annotations on the maps. It should be noted that many of these features had by this point been verified by field expeditions. By consulting existing maps and getting ground truth in person, they had made sure that these weren’t phantom structures or wishful thinking. “We’re confident that they’re all there,” he told me.

“Next is the quantitative step,” he continued. “You measure the length and the areas and you put it all together, and you start analyzing them like you’d analyze other data set: the structure density of some area, the size of urban sprawl or agricultural fields. Finally we even figured a way to quantify the potential production of agriculture.”

This is the point where the imagery starts to go from point cloud to academic study. After all, it’s well known that the Maya had a large city in this area; it’s been intensely studied for decades. But the Pacunam (which stands for Patrimonio Cultural y Natural Maya) study was meant to advance beyond the traditional methods employed previously.

“It’s a huge data set. It’s a huge cross-section of the Maya lowlands,” Estrada-Belli said. “Big data is the buzzword now, right? You truly can see things that you would never see if you only looked at one site at a time. We could never have put together these grand patterns without lidar.”

“For example, in my area, I was able to map 47 square kilometers over the course of 15 years,” he said, slightly wistfully. “And in two weeks the lidar produced 308 square kilometers, to a level of detail that I could never match.”

As a result the paper includes all kinds of new theories and conclusions, from population and economy estimates, to cultural and engineering knowledge, to the timing and nature of conflicts with neighbors.

The resulting report doesn’t just advance the knowledge of Mayan culture and technology, but the science of archaeology itself. It’s iterative, of course, like everything else — Estrada-Belli noted that they were inspired by work done by colleagues in Belize and Cambodia; their contribution, however, exemplifies new approaches to handling large areas and large data sets.

The more experiments and field work, the more established these methods will become, and the greater they will be accepted and replicated. Already they have proven themselves invaluable, and this study is perhaps the best example of lidar’s potential in the field.

WTF is lidar?

“We simply would not have seen these massive fortifications. Even on the ground, many of their details remain unclear. Lidar makes most human-made features clear, coherent, understandable,” explained co-author Stephen Houston, of Brown University, in an email. “AI and pattern recognition may help to refine the detection of features, and drones may, we hope, bring down the cost of this technology.”

“These technologies are important not only for discovery, but also for conservation,” pointed out co-author, Ithaca College’s Thomas Garrison, in an email. “3D scanning of monuments and artifacts provide detailed records and also allow for the creation of replicas via 3D printing.”

Lidar imagery can also show the extent of looting, he wrote, and help cultural authorities provide against it by being aware of relics and sites before the looters are.

The researchers are already planning a second, even larger set of flyovers, founded on the success of the first experiment. Perhaps by the time the initial physical work is done the trendier tools of the last few years will make themselves applicable.

“I doubt the airplanes are going to get less expensive but the instruments will be more powerful,” Estrada-Belli suggested. “The other line is the development of artificial intelligence that can speed up the project; at least it can rule out areas, so we don’t waste any time, and we can zero in on the areas with the greatest potential.”

He’s also excited by the idea of putting the data online so citizen archaeologists can help pore over it. “Maybe they don’t have the same experience we do, but like artificial intelligence they can certainly generate a lot of good data in a short time,” he said.

But as his colleagues point out, even years in this line of work are necessarily preliminary.

“We have to emphasize: it’s a first step, leading to innumerable ideas to test. Dozens of doctoral dissertations,” wrote Houston. “Yet there must always be excavation to look under the surface and to extract clear dates from the ruins.”

“Like many disciplines in the social sciences and humanities, archaeology is embracing digital technologies. Lidar is just one example,” wrote Garrison. “At the same time, we need to be conscious of issues in digital archiving (particularly the problem of obsolete file formatting) and be sure to use technology as a complement to, and not a replacement for methods of documentation that have proven tried and true for over a century.”

The researchers’ paper was published today in Science; you can learn about their conclusions (which are of more interest to the archaeologists and anthropologists among our readers) there, and follow other work being undertaken by the Fundación Pacunam at its website.

Source: gadgets

How aerial lidar illuminated a Mayan megalopolis Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but…

[thegloober]

How aerial lidar illuminated a Mayan megalopolis

Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but lidar has proven transformative. The latest accomplishment using laser-based imaging maps thousands of square kilometers of an ancient Mayan city once millions strong, but the researchers make it clear that there’s no technological substitute for experience and a good eye.

The Pacunam Lidar Initiative began two years ago, bringing together a group of scholars and local authorities to undertake the largest yet survey of a protected and long-studied region in Guatemala. Some 2,144 square kilometers of the Maya Biosphere Reserve in Petén were scanned, inclusive of and around areas known to be settled, developed, or otherwise of importance.

Preliminary imagery and data illustrating the success of the project were announced earlier this year, but the researchers have now performed their actual analyses on the data, and the resulting paper summarizing their wide-ranging results has been published in the journal Science.

The areas covered by the initiative, as you can see, spread over perhaps a fifth of the country.

“We’ve never been able to see an ancient landscape at this scale all at once. We’ve never had a dataset like this. But in February really we hadn’t done any analysis, really, in a quantitative sense,” co-author Francisco Estrada-Belli, of Tulane University, told me. He worked on the project with numerous others, including his colleagues Marcello Canuto and Stephen Houston. “Basically we announced we had found a huge urban sprawl, that we had found agricultural features on a grand scale. After another 9 months of work we were able to quantify all that and to get some numerical confirmations for the impressions we’d gotten.”

“It’s nice to be able to confirm all our claims,” he said. “They may have seemed exaggerated to some.”

The lidar data was collected not by self-driving cars, which seem to be the only vehicles bearing lidar we ever hear about, nor even by drones, but by traditional airplane. That may sound cumbersome, but the distances and landscapes involved permitted nothing else.

“A drone would never have worked — it could never have covered that area,” Estrada-Belli explained. “In our case it was actually a twin engine plane flown down from Texas.”

The plane would made dozens of passes over a given area, a chosen “polygon” perhaps 30 kilometers long and 20 wide. Mounted underneath was “a Teledyne Optech Titan MultiWave multichannel, multi-spectral, narrow-pulse width lidar system,” which pretty much says it all: this is a heavy duty instrument, the size of a refrigerator. But you need that kind of system to pierce the canopy and image the underlying landscape.

The many overlapping passes were then collated and calibrated into a single digital landscape of remarkable detail.

“It identified features that I had walked over — a hundred of times!” he laughed. “Like a major causeway, I walked over it, but it was so subtle, and it was covered by huge vegetation, underbrush, trees, you know, jungle — I’m sure that in another 20 years I wouldn’t have noticed it.”

But these structures don’t identify themselves. There’s no computer labeling system that looks at the 3D model and says, “this is a pyramid, this is a wall,” and so on. That’s a job that only archaeologists can do.

“It actually begins with manipulating the surface data,” Estrada-Belli said. “We get these surface models of the natural landscape; each pixel in the image is basically the elevation. Then we do a series of filters to simulate light being projected on it from various angles to enhance the relief, and we combine these visualizations with transparencies and different ways of sharpening or enhancing them. After all this process, basically looking at the computer screen for a long time, then we can start digitizing it.”

“The first step is to visually identify features. Of course, pyramids are easy, but there are subtler features that, even once you identify them, it’s hard to figure out what they are.”

The lidar imagery revealed, for example, lots of low linear features that could be man-made or natural. It’s not always easy to tell the difference, but context and existing scholarship fill in the gaps.

“Then we proceeded to digitize all these features… there were 61,000 structures, and everything had to be done manually,” Estrada-Belli said — in case you were wondering why it took nine months. “There’s really no automation because the digitizing has to be done based on experience. We looked into AI, and we hope that maybe in the near future we’ll be able to apply that, but for now an experienced archaeologist’s eye can discern the features better than a computer.”

You can see the density of the annotations on the maps. It should be noted that many of these features had by this point been verified by field expeditions. By consulting existing maps and getting ground truth in person, they had made sure that these weren’t phantom structures or wishful thinking. “We’re confident that they’re all there,” he told me.

“Next is the quantitative step,” he continued. “You measure the length and the areas and you put it all together, and you start analyzing them like you’d analyze other dataset: the structure density of some area, the size of urban sprawl or agricultural fields. Finally we even figured a way to quantify the potential production of agriculture.”

This is the point where the imagery starts to go from point cloud to academic study. After all, it’s well known that the Maya had a large city in this area; it’s been intensely studied for decades. But the Pacunam (which stands for Patrimonio Cultural y Natural Maya) study was meant to advance beyond the traditional methods employed previously.

“It’s a huge dataset. It’s a huge cross section of the Maya lowlands,” Estrada-Belli said. “Big data is the buzzword now, right? You truly can see things that you would never see if you only looked at one site at a time. We could never have put together these grand patterns without lidar.”

“For example, in my area, I was able to map 47 square kilometers over the course of 15 years,” he said, slightly wistfully. “And in two weeks the lidar produced 308 square kilometers, to a level of detail that I could never match.”

As a result the paper includes all kinds of new theories and conclusions, from population and economy estimates, to cultural and engineering knowledge, to the timing and nature of conflicts with neighbors.

The resulting report doesn’t just advance the knowledge of Mayan culture and technology, but the science of archaeology itself. It’s iterative, of course, like everything else — Estrada-Belli noted that they were inspired by work done by colleagues in Belize and Cambodia; their contribution, however, exemplifies new approaches to handling large areas and large datasets.

The more experiments and field work, the more established these methods will become, and the greater they will be accepted and replicated. Already they have proven themselves invaluable, and this study is perhaps the best example of lidar’s potential in the field.

“We simply would not have seen these massive fortifications. Even on the ground, many of their details remain unclear. Lidar makes most human-made features clear, coherent, understandable,” explained co-author Stephen Houston (also from Tulane) in an email. “AI and pattern recognition may help to refine the detection of features, and drones may, we hope, bring down the cost of this technology.”

“These technologies are important not only for discovery, but also for conservation,” pointed out co-author Thomas Garrison in an email. “3D scanning of monuments and artifacts provide detailed records and also allow for the creation of replicas via 3D printing.”

Lidar imagery can also show the extent of looting, he wrote, and help cultural authorities provide against it by being aware of relics and sites before the looters are.

The researchers are already planning a second, even larger set of flyovers, founded on the success of the first experiment. Perhaps by the time the initial physical work is done the trendier tools of the last few years will make themselves applicable.

“I doubt the airplanes are going to get less expensive but the instruments will be more powerful,” Estrada-Belli suggested. “The other line is the development of artificial intelligence that can speed up the project; at least it can rule out areas, so we don’t waste any time, and we can zero in on the areas with the greatest potential.”

He’s also excited by the idea of putting the data online so citizen archaeologists can help pore over it. “Maybe they don’t have the same experience we do, but like artificial intelligence they can certainly generate a lot of good data in a short time,” he said.

But as his colleagues point out, even years in this line of work are necessarily preliminary.

“We have to emphasize: it’s a first step, leading to innumerable ideas to test. Dozens of doctoral dissertations,” wrote Houston. “Yet there must always be excavation to look under the surface and to extract clear dates from the ruins.”

“Like many disciplines in the social sciences and humanities, archaeology is embracing digital technologies. Lidar is just one example,” wrote Garrison. “At the same time, we need to be conscious of issues in digital archiving (particularly the problem of obsolete file formatting) and be sure to use technology as a complement to, and not a replacement for methods of documentation that have proven tried and true for over a century.”

The researchers’ paper was published today in Science; you can learn about their conclusions (which are of more interest to the archaeologists and anthropologists among our readers) there, and follow other work being undertaken by the Fundación Pacunam at its website.

Source: https://bloghyped.com/how-aerial-lidar-illuminated-a-mayan-megalopolis/

[roberttbertton]

Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but lidar has proven transformative. The latest accomplishment using laser-based imaging maps thousands of square kilometers of an ancient Mayan city once millions strong, but the researchers make it clear that there’s no technological substitute for experience and a good eye.

The Pacunam Lidar Initiative began two years ago, bringing together a group of scholars and local authorities to undertake the largest yet survey of a protected and long-studied region in Guatemala. Some 2,144 square kilometers of the Maya Biosphere Reserve in Petén were scanned, inclusive of and around areas known to be settled, developed, or otherwise of importance.

Preliminary imagery and data illustrating the success of the project were announced earlier this year, but the researchers have now performed their actual analyses on the data, and the resulting paper summarizing their wide-ranging results has been published in the journal Science.

The areas covered by the initiative, as you can see, spread over perhaps a fifth of the country.

“We’ve never been able to see an ancient landscape at this scale all at once. We’ve never had a dataset like this. But in February really we hadn’t done any analysis, really, in a quantitative sense,” co-author Francisco Estrada-Belli, of Tulane University, told me. He worked on the project with numerous others, including his colleagues Marcello Canuto and Stephen Houston. “Basically we announced we had found a huge urban sprawl, that we had found agricultural features on a grand scale. After another 9 months of work we were able to quantify all that and to get some numerical confirmations for the impressions we’d gotten.”

“It’s nice to be able to confirm all our claims,” he said. “They may have seemed exaggerated to some.”

The lidar data was collected not by self-driving cars, which seem to be the only vehicles bearing lidar we ever hear about, nor even by drones, but by traditional airplane. That may sound cumbersome, but the distances and landscapes involved permitted nothing else.

“A drone would never have worked — it could never have covered that area,” Estrada-Belli explained. “In our case it was actually a twin engine plane flown down from Texas.”

The plane would made dozens of passes over a given area, a chosen “polygon” perhaps 30 kilometers long and 20 wide. Mounted underneath was “a Teledyne Optech Titan MultiWave multichannel, multi-spectral, narrow-pulse width lidar system,” which pretty much says it all: this is a heavy duty instrument, the size of a refrigerator. But you need that kind of system to pierce the canopy and image the underlying landscape.

The many overlapping passes were then collated and calibrated into a single digital landscape of remarkable detail.

“It identified features that I had walked over — a hundred of times!” he laughed. “Like a major causeway, I walked over it, but it was so subtle, and it was covered by huge vegetation, underbrush, trees, you know, jungle — I’m sure that in another 20 years I wouldn’t have noticed it.”

But these structures don’t identify themselves. There’s no computer labeling system that looks at the 3D model and says, “this is a pyramid, this is a wall,” and so on. That’s a job that only archaeologists can do.

“It actually begins with manipulating the surface data,” Estrada-Belli said. “We get these surface models of the natural landscape; each pixel in the image is basically the elevation. Then we do a series of filters to simulate light being projected on it from various angles to enhance the relief, and we combine these visualizations with transparencies and different ways of sharpening or enhancing them. After all this process, basically looking at the computer screen for a long time, then we can start digitizing it.”

“The first step is to visually identify features. Of course, pyramids are easy, but there are subtler features that, even once you identify them, it’s hard to figure out what they are.”

The lidar imagery revealed, for example, lots of low linear features that could be man-made or natural. It’s not always easy to tell the difference, but context and existing scholarship fill in the gaps.

“Then we proceeded to digitize all these features… there were 61,000 structures, and everything had to be done manually,” Estrada-Belli said — in case you were wondering why it took nine months. “There’s really no automation because the digitizing has to be done based on experience. We looked into AI, and we hope that maybe in the near future we’ll be able to apply that, but for now an experienced archaeologist’s eye can discern the features better than a computer.”

You can see the density of the annotations on the maps. It should be noted that many of these features had by this point been verified by field expeditions. By consulting existing maps and getting ground truth in person, they had made sure that these weren’t phantom structures or wishful thinking. “We’re confident that they’re all there,” he told me.

“Next is the quantitative step,” he continued. “You measure the length and the areas and you put it all together, and you start analyzing them like you’d analyze other dataset: the structure density of some area, the size of urban sprawl or agricultural fields. Finally we even figured a way to quantify the potential production of agriculture.”

This is the point where the imagery starts to go from point cloud to academic study. After all, it’s well known that the Maya had a large city in this area; it’s been intensely studied for decades. But the Pacunam (which stands for Patrimonio Cultural y Natural Maya) study was meant to advance beyond the traditional methods employed previously.

“It’s a huge dataset. It’s a huge cross section of the Maya lowlands,” Estrada-Belli said. “Big data is the buzzword now, right? You truly can see things that you would never see if you only looked at one site at a time. We could never have put together these grand patterns without lidar.”

“For example, in my area, I was able to map 47 square kilometers over the course of 15 years,” he said, slightly wistfully. “And in two weeks the lidar produced 308 square kilometers, to a level of detail that I could never match.”

As a result the paper includes all kinds of new theories and conclusions, from population and economy estimates, to cultural and engineering knowledge, to the timing and nature of conflicts with neighbors.

The resulting report doesn’t just advance the knowledge of Mayan culture and technology, but the science of archaeology itself. It’s iterative, of course, like everything else — Estrada-Belli noted that they were inspired by work done by colleagues in Belize and Cambodia; their contribution, however, exemplifies new approaches to handling large areas and large datasets.

The more experiments and field work, the more established these methods will become, and the greater they will be accepted and replicated. Already they have proven themselves invaluable, and this study is perhaps the best example of lidar’s potential in the field.

WTF is lidar?

“We simply would not have seen these massive fortifications. Even on the ground, many of their details remain unclear. Lidar makes most human-made features clear, coherent, understandable,” explained co-author Stephen Houston (also from Tulane) in an email. “AI and pattern recognition may help to refine the detection of features, and drones may, we hope, bring down the cost of this technology.”

“These technologies are important not only for discovery, but also for conservation,” pointed out co-author Thomas Garrison in an email. “3D scanning of monuments and artifacts provide detailed records and also allow for the creation of replicas via 3D printing.”

Lidar imagery can also show the extent of looting, he wrote, and help cultural authorities provide against it by being aware of relics and sites before the looters are.

The researchers are already planning a second, even larger set of flyovers, founded on the success of the first experiment. Perhaps by the time the initial physical work is done the trendier tools of the last few years will make themselves applicable.

“I doubt the airplanes are going to get less expensive but the instruments will be more powerful,” Estrada-Belli suggested. “The other line is the development of artificial intelligence that can speed up the project; at least it can rule out areas, so we don’t waste any time, and we can zero in on the areas with the greatest potential.”

He’s also excited by the idea of putting the data online so citizen archaeologists can help pore over it. “Maybe they don’t have the same experience we do, but like artificial intelligence they can certainly generate a lot of good data in a short time,” he said.

But as his colleagues point out, even years in this line of work are necessarily preliminary.

“We have to emphasize: it’s a first step, leading to innumerable ideas to test. Dozens of doctoral dissertations,” wrote Houston. “Yet there must always be excavation to look under the surface and to extract clear dates from the ruins.”

“Like many disciplines in the social sciences and humanities, archaeology is embracing digital technologies. Lidar is just one example,” wrote Garrison. “At the same time, we need to be conscious of issues in digital archiving (particularly the problem of obsolete file formatting) and be sure to use technology as a complement to, and not a replacement for methods of documentation that have proven tried and true for over a century.”

The researchers’ paper was published today in Science; you can learn about their conclusions (which are of more interest to the archaeologists and anthropologists among our readers) there, and follow other work being undertaken by the Fundación Pacunam at its website.

Source TechCrunch https://ift.tt/2OYGQsR

How aerial lidar illuminated a Mayan megalopolis – BerTTon Archaeology may not be the most likely place to find the latest in technology — AI and robots are of dubious utility in the painstaking fieldwork involved — but…