Imagery and Remote Sensing Blog

cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

Other Boards in This Place

Latest Activity

(55 Posts)
VinayViswambharan
Esri Contributor

With the firehose of imagery that’s streaming down daily from a variety of sensors, the need for using AI to automate feature extraction is only increasing. To make sure your organization is prepared, Esri is taking AI to the next level. We are very excited to announce the release of ready-to-use geospatial AI models on the ArcGIS Living Atlas.

Article Overview: Esri is bringing ready-to-use deep learning models to our user community through ArcGIS Online.

To kick it off, we’ve added three models — building footprint extraction and land cover classification from satellite imagery, and another model to classify points representing trees in point cloud datasets.

With the existing capabilities in ArcGIS, you’ve been able to train over a dozen deep learning models on geospatial datasets and derive information products using the ArcGIS API for Python or ArcGIS Pro, and scale up processing using ArcGIS Image Server.

Building footprints automatically extracted using the new deep learning model
Building footprints automatically extracted using the new deep learning model

These newly released models are a game changer! They have been pre-trained by Esri on huge volumes of data and can be readily used (no training required!) to automate the tedious task of digitizing and extracting geographical features from satellite imagery and point cloud datasets. They bring the power of AI and deep learning to the Esri user community. What’s more, these deep learning models are accessible for anyone with an ArcGIS Online subscription at no additional cost.

 

Using the models

Using these models is simple. You can use geoprocessing tools (such as the Detect Objects Using Deep Learning tool) in ArcGIS Pro with the imagery models.  Point the tool to the imagery and the downloaded model, and that’s about it – deep learning has never been this easy! A GPU, though not necessary, can help speed things up. With ArcGIS Enterprise, you can scale up the inferencing using Image Server.

Using the model in ArcGIS Pro
Using the building footprint extraction model in ArcGIS Pro

Coming soon, you’ll be able to consume the model directly in ArcGIS Online Imagery and run it against your own uploaded imagery—all without an ArcGIS Enterprise deployment. The 3D Basemaps solution is also being enhanced to use the tree point classification model and create realistic 3D tree models from raw point clouds.

 

How can you benefit from these deep learning models?

It probably goes without saying that manually extracting features from imagery—like digitizing footprints or generating land cover maps—is time-consuming. Deep learning automates the process and significantly minimizes the manual interaction needed to create these products. However, training your own deep learning model can be complicated – it needs a lot of data, extensive computing resources, and knowledge of how deep learning works.

 

Sample building footprints extracted - Woodland, CA
Sample building footprints extracted - Woodland, CA

With ready-to-use models, you no longer have to invest time and energy into manually extracting features or training your own deep learning model. These models have been trained on data from a variety of geographies and work well across them. As new imagery comes in, you can readily extract features at the click of a button, and produce layers of GIS datasets for mapping, visualization and analysis.

Sample building footprints extracted - Palm Islands, Dubai
Sample building footprints extracted - Palm Islands, Dubai

 

Get to know the first three models we released

Three deep learning models are now available in ArcGIS Online. (Watch for more models in the future!). These models are available as deep learning packages (DLPKs) that can be used with ArcGIS Pro, Image Server and ArcGIS API for Python.

1. Building Footprint Extraction model is used to extract building footprints from high resolution satellite imagery. While its designed for the contiguous United States, it performs fairly well in other parts of the globe.

The model performs fairly well in other parts of the globe. Results from Ulricehamn, Sweden.
The model performs fairly well in other parts of the globe. Results from Ulricehamn, Sweden.

Here’s a story map presenting some of the results. Building footprint layers are useful for creating basemaps and in analysis workflows for urban planning and development, insurance, taxation, change detection, and infrastructure planning.

2. Landcover Classification model is used to create a land cover product using Landsat 8 imagery. The classified land cover will have the same classes as the National Land Cover Database. The resulting land cover maps are useful for urban planning, resource management, change detection and agriculture.

Classified landcover map using Landsat 8 imagery
Classified landcover map using Landsat 8 imagery

This generic model is has been trained on the National Land Cover Database (NLCD) 2016 with the same Landsat 8 scenes that were used to produce the database. Land cover classification is a complex exercise and is hard to capture using traditional means. Deep learning models have a high capacity to learn these complex semantics and give superior results.

3. Tree Point Classification model can be used to classify points representing trees in point cloud datasets.

Interactive 3D basemap created by employing tree point classification model.
3D scene created by employing tree point classification model.

Classifying tree points is useful for creating high quality 3D basemaps, urban planning and forestry workflows.

 

Next steps

Try out the deep learning models in ArcGIS Living Atlas for yourself. Read more detailed instructions for using the deep learning models in ArcGIS. Have questions? Let us know on GeoNet how they are working for you, and which other feature extraction tasks you’d like AI to do for you!

more
0 3 958
JeffLiedtke
Occasional Contributor II

Raster analytics using ArcGIS Enterprise is a flexible raster processing, storage, and sharing system that employs distributed computing and storage technology. Use raster analytics to apply the rich set of raster processing tools and functions offered in ArcGIS, build your own custom functions and tools, or combine multiple tools and functions into raster processing chains to execute your custom algorithms on large collections of raster data. Source data and processed results are stored, published and shared across your enterprise accordingly.

This extensive capability can be further expanded by leveraging cloud computing capabilities and resources.  The net result: image processing and analysis jobs that used to take days or weeks can now be done in minutes or hours, and jobs that were impossibly large or too daunting are now within easy reach.

What can raster analytics do?

By leveraging ArcGIS Enterprise, raster analytics enables you to:

  • Quickly process massive imagery or raster datasets in a scalable environment
  • Execute advanced, customized raster analysis
  • Share results with individuals, departments, and organizations within or outside your enterprise

Raster analytics is ArcGIS Image Server configured for raster analysis in a processing and storage environment that maximizes processing speed and efficiency.  Built-in tools and functions cover preprocessing, orthorectification and mosaicking, remote sensing analysis, and an extensive range of math and trigonometry operators; your custom functions can extend the platform’s analytical capabilities even further.

Fully utilize your existing ArcGIS Image Server on-site, or exploit the elastic processing and storage capacity of cloud computing and storage platforms such as Amazon Web Services and Microsoft Azure to dynamically increase or reduce your capacity depending on the size and urgency of your projects.  The scalable environment of raster analytics empowers you to implement computationally intensive image processing that used to be out of reach or cost-prohibitive. This implementation saves you time, money, and resources.

Raster analytics is also designed to streamline and simplify collaboration and sharing. Users across your enterprise can contribute data, processing models, and expertise to your imagery project, and share results with individuals, departments, and organizations in your enterprise.

Finally, Raster analytics using ArcGIS Enterprise integrates your image processing and analysis with the world’s leading GIS platform, and allows users to seamlessly draw on the world’s largest collection of online digital maps and imagery.

How does raster analytics work?

ArcGIS Image Server configured for the role of raster analytics provides software and user interfaces to organize and manage your processing, storage, and sharing of raster and feature data, maps, and other geographic information on a variety of devices. This integrated system manages the dissemination of processing and storage of results (1) on-premises and behind the firewall for classified deployments, (2) in cloud processing and storage environments, or (3) a combination of both environments.

The foundation of raster analytics is ArcGIS Enterprise, which includes an Enterprise GIS Portal, ArcGIS Data Store, Image Server configured for raster analytics, raster data store and ArcGIS Web Adaptor. ArcGIS Enterprise integrates the components of the raster analytics system to support scalable, real-world workflows.

Scale your powerful processing and storage capabilities by deploying ArcGIS Enterprise in the cloud via Microsoft Azure or Amazon Web Services (AWS). For example, you can automatically scale capacity up and down according to conditions you define, or automatically dispense application traffic across multiple instances for better performance. ArcGIS Enterprise makes deployment easier by providing Cloud Builder for Microsoft Azure or AWS CloudFormation with sample templates to configure and deploy your system in the cloud.

Develop, test and optimize your raster processing chains using Esri’s rich set of more than 200 functions and tools in the familiar ArcGIS Desktop or web map viewer. Once verified and optimized in the dynamic on-the-fly processing environment, submit your processing chain to ArcGIS Portal, which manages the distribution of processing, storage, and publication of results.

The ideal deployment of raster analytics is comprised of three server sites to perform the primary roles of the portal host server, raster analysis server, and the image hosting server. Two licenses are required for raster analytics, ArcGIS Enterprise and Image Server.

Raster Analytics System Diagram

The hosting server is your portal’s server for standard portal administration and operations such as managing and dispensing processing, storage, and publication of results to raster analysis servers, image servers, and data stores.  It also hosts the ArcGIS Data Store for GIS data and allows users to publish data and maps to a wider audience as web services.

Raster analytics jobs are processed by image servers dedicated for raster analytics, comprised of one or more servers, each with multiple processing cores. The image processing and raster analytics tasks are distributed at the tile level or scene level depending on the tools and functions used. Raster analytics manages the processing results to either the ArcGIS Data Store on the hosting server for feature data products, or to the raster data store for imagery and raster data products. The raster data store can be implemented using distributed file share storage or using cloud storage such as Amazon S3 or Microsoft Azure blob storage.

The image hosting server hosts all the image services generated by the raster analysis server. It includes the raster data store configured with the Image Server Manager, which manages distributed file share storage and cloud storage of image services using Amazon S3 or Microsoft Azure blob storage. The image hosting server stores and returns results requested by members of your enterprise.

System configuration apps assign the roles of the servers and data stores, and also set the permission structure for all the users across your enterprise. This facilitates optimal flexibility in configuring and implementing your raster analytics system to address specific projects. Multiple servers can be scaled up for raster analytics processing and storage as required.

See the tutorial to set up a base ArcGIS Enterprise deployment.

More Information

To learn more about raster analytics using ArcGIS Enterprise and ArcGIS Image Server, check out this video.

Explore these help topics to get started with raster analytics:

To see how raster analytics is being used, check out the Chesapeake Conservancy and Distributed Image Processing presentation, or attend the Plenary session at the 2017 Esri User Conference in San Diego to hear about Chesapeake Conservancy’s experience processing and sharing the entire Chesapeake watershed using raster analytics.

Please plan to attend a few presentations addressing raster analytics at the 2017 Esri User Conference:

Raster Analytics at Esri UC2017

more
1 0 609
JeffLiedtke
Occasional Contributor II

Imagery can add valuable information and context to a wide array of GIS projects. For example, you can detect impervious surfaces for storm water management, map and manage riparian corridors, or track what’s changing in your county. Sometimes, though, incorporating imagery into your GIS can feel overwhelming—how can your system handle that much data?

Enter raster analytics, a distributed processing, storage, and sharing system designed to quickly process large collections of aerial, drone, or satellite imagery, then extract and share meaningful information for critical decision support. Raster analytics can be run locally, but you can also pair it with distributed cloud computing to maximize efficiency. Image processing and analysis jobs that used to take days or weeks can be completed in minutes or hours, bringing imagery projects that were impossibly large or daunting within reach.

Raster analytics leverages ArcGIS Enterprise, expanded with ArcGIS Image Server configured for distributed raster analysis, to integrate the components of the raster analytics system to support scalable, real-world workflows

What can raster analytics do?

By leveraging ArcGIS Enterprise with ArcGIS Image Server, raster analytics enables you to:

  • Quickly process massive imagery or raster datasets in a scalable environment
  • Execute advanced, customized raster analysis
  • Share results with individuals, departments, and organizations within or outside your enterprise

The scalable environment of raster analytics empowers you to perform computationally intensive image processing that would otherwise be out of reach or cost-prohibitive. When implemented on-site, raster analytics uses distributed processing to improve efficiency. You can also maximize efficiency by exploiting cloud platforms such as Amazon Web Services or Microsoft Azure, which allow you to dynamically increase or reduce your capacity based on the size and urgency of your projects.  Either implementation can save you time, money, and resources.

Raster analytics uses all the advanced image processing and analysis capabilities of ArcGIS Pro to maximum advantage. Built-in raster functions cover preprocessing, orthorectification and mosaicking, remote sensing analysis, and an extensive range of math and trigonometry operators, while your custom functions can extend the platform’s analytical capabilities even further.

Raster Analytics System Diagram

Raster analytics is also designed to streamline collaboration and sharing. Users across your enterprise can contribute data, processing models, and expertise to your imagery project, then share results with individuals, departments, and organizations in your enterprise.

Finally, raster analytics integrates your image processing and analysis with the world’s leading GIS platform, and allows users to seamlessly draw on Living Atlas of the World, the world’s largest collection of online digital maps and imagery.

How is raster analytics used today?

The Chesapeake Conservancy, working with the University of Vermont and WorldView Solutions, was tasked by the Chesapeake Bay Program to produce one-meter-resolution land cover maps covering 100,000 square miles of the Chesapeake Bay watershed. These high-resolution land cover maps, which classify natural and man-made landscape features, are crucial for supporting watershed and storm water management, conservation, and for reducing pollution into the bay.

To produce this essential dataset, the Chesapeake Conservancy needed to process over 20 terabytes of raster data and categorize it into twelve land cover types. This project took a daunting 18 months to complete using their local machine resources. As a result, Chesapeake Conservancy is now working with raster analytics in the cloud to make this timeline more efficient and cost-effective going forward.

As a proof of concept, they used raster analytics to produce a persistent one-meter land cover dataset of Kent County, Delaware (798 square miles). The Kent County project—comprised of more than 30GB and 3.8 billion pixels of raster data—ran on a ten-machine cluster, each with twenty cores, and completed in less than 5 minutes. This same job took days to to process on their local machines.

The Chesapeake Conservancy is now engaged in reprocessing the entire Chesapeake watershed to benchmark time and cost savings using raster analytics for the project. Using raster analytics for projects in the future will mean that the Chesapeake Conservancy can accomplish ambitious projects in a timely and cost-effective manner, without having to spend resources to acquire, configure, and maintain a large computing and storage infrastructure.

See the Chesapeake Conservancy and Distributed Image Processing presentation for more details, or check out the Plenary session at the 2017 Esri User Conference in San Diego to hear about Chesapeake Conservancy’s experience processing and sharing the entire Chesapeake watershed using raster analytics

More Information:

To learn more about raster analytics using ArcGIS Enterprise and ArcGIS Image Server, check out this video.

Explore these help topics to get started with raster analytics:

Please plan to attend a couple presentations addressing raster analytics at the 2017 Esri User Conference:

Raster Analytics at Esri UC2017

more
0 0 333