Multiple Data Modalities: Fusion not Confusion

Posted on May 22, 2012 by

While I am truly a great advocate of the phrase, “two head’s are better than one”, and might even expand the idea that “three are better than two”; when it comes to geospatial data I recognize it is a great challenge to create products when considering the enormous amount of information & data available today.

An obvious approach to make the most accurate decisions is to consider all the information we have available; but when it comes to big data and multiple modalities, how is that achieved?  One answer you may have considered is “Data Fusion.” While the topic can mean many things to many people, I generalize to be the ability to make more informed decisions based on the ability to view a single problem from many different points of view.

A recent application to highlight Data Point was a study utilizing LiDAR data with Multi-Spectral Imagery (MSI) to evaluate the proximity of houses to various tree types in the Boulder, CO foothills.  The right tools for this job required the capability to process & analyze the spectral information from the MSI data, the height information from the LiDAR point cloud, and also size, texture, height, and shape of objects within the data.

The process behind this approach was to:

1)      Generate a digital elevation model (DEM), a digital surface model (DSM), and building footprint vector information from the LiDAR point cloud.
2)      Take advantage of the spectral information of the MSI data for tree species differentiation.
3)      Build a layer stack of this information and enter object-space where attributes such as size, texture, height, and shape have meaning.
4)      Process the data sets in context and build a layer composite representing all of the information in a final comprehensive product.


Imagery data courtesy of DigitalGlobe (WorldView-2). LiDAR data courtesy of Boulder Creek CZO and National Center for Airborne Laser Mapping (NCALM).

As you can see, the results clearly differentiate coniferous and deciduous trees while excluding shrubs, impervious surfaces, and undergrowth. The building footprint vector layer is easily overlaid for a comprehensive look at the area of interest.

Do you have a data fusion success story? How has data fusion positively impacted your geospatial analysis?

Posted in Geospatial Data, Remote Sensing | Tagged , , , , , , , , , , | Leave a comment

The Satellite Sentinel Project: A New Template for Documenting War Crimes

Posted on May 15, 2012 by

Everyday unique applications for geospatial imagery and image analysis are being developed, outside of traditional applications, to understand what is happening around the world.  Currently, geospatial imagery and GIS are playing a role in the work to end the humanitarian crisis in Sudan. A group created by Not on Our Watch, Enough, the Harvard Humanitarian Initiative, DigitalGlobe, and Google, the Satellite Sentinel Project (SSP) is working on “deterring a return to full-scale civil war between northern and southern Sudan and deterring and documenting threats to civilians along both sides of the border. SSP focuses world attention on mass atrocities in Sudan and uses its imagery and analysis to generate rapid responses on human rights and human security concerns.” (SSP)

The concept of utilizing commercial satellite imagery to monitor a country’s activities is not a new one; however according to the Satellite Sentinel Project’s web site “SSP is the first sustained public effort to systematically monitor and report on potential hotspots and threats to human security in near real-time.” This is a shift in the type of people who are using satellite imagery for surveillance and may mark a new era in civilian efforts to bring the atrocities of a government regime to the world stage. While mapping initiatives and geo-enabled applications are markets that are growing commercially, the SSP represents a new breed of imagery and analysis consumer; in particular one where small groups of civilian GIS experts are being leveraged to provide information regarding a political issue that is being monitored by non-GIS and non-governmental entities.

In an age of declining domestic budgets, the SSP represents a new way forward for both the GIS industry and the political activists who are looking to bring attention to political and humanitarian activities throughout the world. Only time will tell just how successful this project is in achieving its goals and to what extent imagery and imagery analysis can be leveraged for similar activities in the future. However, the SSP has already achieved the goal of providing a new template for civilian entities to leverage non-governmental resources to document war crimes and to affect political change.

How else do you see geospatial imagery and image analysis impacting humanitarian efforts?

Posted in Geospatial Data | Tagged , , , , , , , , , , | 3 Comments

The VISeon Project

Posted on May 8, 2012 by

As demand for commercial and industry software services in the cloud has grown, so has the demand for cloud-based geospatial image analysis services. This demand has increased because it gives a wider user-base easy access to the tools needed to analyze geospatial imagery and make critical decisions, independent of where they are located. To explore the relationship between web-based services and geospatial products, we began developing the “VISeon Project”, which demonstrates the capabilities of our ENVI Services Engine in real-world cloud based applications. The ENVI Services Engine is a web-based platform that gives users access to ENVI image analysis tools and capabilities on variety of devices.

The goals for the project were to:

  • Develop an enterprise system based on OGC standards and highlight the flexibility of the engine’s lightweight REST interface for integration.
  • Demonstrate data discovery, visualization and processing through intuitive web and mobile clients.
  • Illustrate how ENVI analytic capabilities could be accessed through simple apps accessing an enterprise server.

Using “Agile” development methods, which are “based on iterative and incremental development”, our team was able to meet the project goals on a shorten timeline. In addition to developing a flexible web-based services engine we wanted to demonstrate that such an engine could be fully interoperable, work with other COTS products, and could be integrated with other applications and architectures.

During development, the VISeon Project, ENVI Services Engine, and associated apps were integrated with Esri’s ArcGIS for Server and BAE’s GXP Xplorer. We have since deployed Project VISeon in the Amazon Cloud to make it more readily accessible for demonstrations and continued development.  Through the experimental development and deployment of Project VISeon, we have been able to see image analysis capabilities accessible in the cloud.  This experience helps us understand how such capabilities would be used to address online and on-demand need of geospatial imagery users.

How do you see cloud based services impacting your image analysis?

Posted in Enterprise Solutions, Geospatial Data | Tagged , , , , , , , , , , , | Leave a comment

Newer! Faster! Easier! ENVI 5 Feature Extraction!

Posted on May 1, 2012 by

One of my favorite features that has been added to ENVI in the past several years is the Feature Extraction workflow.  That tool segments an input image into polygonal objects, then classifies those objects into categories using the spatial, spectral, and/or texture attributes that it calculates for each object.  So, what I’m most excited for in the new ENVI 5 release are some improvements that will make the Feature Extraction workflow even better.

For one thing, new high-speed multi-threaded processing makes the performance much faster.  Anyone else who has waited a couple of days for the processing on a large image to finish will understand my enthusiasm for this change.  I’m told that in some cases, the segmentation can be many times faster than it is in ENVI 4.8.  That’s pretty impressive, and very welcome.

Also, I really like the changes to the interface, which place the segmentation and merge parameters, as well as some other preprocessing parameters, on the same initial dialog.  This change means that you can play around with interactions of the various parameters, checking out the results in the instant preview.  Then when you’ve figured out the optimal settings, you can run the segmentation and merge steps all in one shot.  That is going to save me a bundle of time right there.

GUI for feature extraction in ENVI 5

The new interface for the feature extraction workflow in ENVI 5.

Finally, it’s also now possible to output some intermediate steps, such as the attribute images.  Those images contain a whole lot of information, and I can imagine that people will come up with all kinds of alternate ways of using them outside of the rest of ENVI’s Feature Extraction workflow.

As long as I have your attention, I also want to mention that the Exelis VIS Tech Support team has been working hard writing Help Articles to help people find answers to ENVI 5 questions that we think may be common.  So, if you run into any specific technical questions about ENVI 5, you might try checking the Help Article database, to see if your question has already been answered.

Posted in Geospatial Data, Remote Sensing | Tagged , , , , , , , , | 1 Comment

VISualize 2012: Climate Change & Environmental Monitoring

Posted on April 24, 2012 by

If you’re like me you probably have the occasion to attend conferences and trade shows throughout the year and learn how imagery and data are used in a variety of ways across industries.   But where can you learn about Mapping Mars with CRISM and IDL, Monitoring Coastal Wetlands with Hyperspectral Imagery, and Massively Parallelized Pathfinding to Support Archaeological Research?   Those topics were just a handful of the presentations at the 2011 VISualize conference, our annual IDL & ENVI user group meeting held at the World Wildlife Fund office in Washington DC.

This June 18 and 19 we will again host VISualize 2012 at the World Wildlife Foundation in Washington DC.  In a bit of detour from the anything goes slate of presentations of the last few years, this years’ conference will focus on Environmental Monitoring.  For two days our users from industry and academia will discuss how geospatial technology is helping to understand and solve climate change and environmental monitoring challenges.  Anticipated topics include global deforestation and REDD+, global flooding and impending water shortages, atmospheric and climate applications, and data analysis and visualization.

Conference registration is still open and speaker slots are still available.  Do you have an interesting geospatial application that utilizes ENVI or IDL?  Check out the call for abstracts and join us in June!

Posted in Remote Sensing | Tagged , , , , , , , , , , , , , , | Leave a comment

GIS Trends & Topics: MidAmerica Geospatial Symposium

Posted on April 17, 2012 by

As I sit here planning a trip to Kansas City to attend the biennial MidAmerica GIS Symposium, I am poring over the meeting collateral, program schedule, and course descriptions and trying to find the best way to highlight how imagery fits into the GIS community’s ground-breaking and every-day challenges. What I have found is a sense of enthusiasm about recent GIS advances and a sense of excitement about the future of GIS.

While thinking about where the imagery component fits as part of a solution to the broader GIS community’s needs, I thought I would share some of the images that came to mind while reading about the program topics. All of these images are examples of how some people might be utilizing imagery to develop geospatial products. The programs for the symposium are divided into the following five categories.

GIS in Public Safety and Health:  This image was derived from QuickBird data courtesy of Digital Globe. The light blue areas indicate inland water after hurricane Katrina.  The green areas also indicate flooding to a lesser-degree.

Public Face of GIS:  This scene, courtesy of Landsat 7, displays an area of Big Horn basin in Wyoming  including a contour vector overlay that is exported to Google Earth.

Smart Growth – Urban Planning & Growth:  The first image to come to mind when considering urban planning is this dark rooftop feature extraction result of a suburban pan-sharpened QuickBird dataset courtesy o f Digital Globe.

GIS Behind the Scenes: A few of the program topics include a pointer to the next generation USGS digital topographic maps that I thought deserved to be shared: Digital Raster Graphics (DRG) format (formerly hard-copy topo) maps are now available via this site!

Technology and Trends – The Future of GIS: With the movement of GIS into the cloud and mobile application deployment of GIS technology, it is hard to not feel excitement about the future. But also, what about the exciting things happening in the present? With increasing GIS support for Lidar and the noticeable weight placed on the symposium topics in this category I couldn’t help but include the following image that is a 3D rendering of downtown San Diego from a Lidar LAS point cloud courtesy of  USGS.

I am very excited to attend the symposium. Will you be going? What are you most looking forward to see?  How do you see imagery fitting into your daily work? Please stop by and say hello!

Posted in Geospatial Data | Tagged , , , , , , , , , , , , , | Leave a comment

Environmental Conservation and Geospatial Image Analysis

Posted on April 10, 2012 by

In his recent post, my colleague, Peter McIntosh wrote about the different markets where geospatial software provides solutions.   For many geospatial imagery users monitoring and quantifying change is a very important task.   Through my work with academic institutions and environmental organizations, I have noticed the same need for accurate change detection results.

The Nature Conservancy and some of its member affiliates are using image analysis software to aid researchers and scientists in studying some of our planet’s critical habitats.  Additionally, organizations such as the Wildlife Conservation Society, Jane Goodall Institute, and Conservation International are using also using geospatial image analysis tools along with government and commercial satellite imagery to map land cover and detect changes across the globe.

Using archival imagery with image classification tools enables researchers to set a baseline of a habitat going back years.  With this type of baseline, both reforestation and deforestation can me mapped and quantified.   Other areas of application include mapping agriculture encroachment into native forest, development of urban areas, roads and footpaths development, and detecting mining encampments in protected areas home to endangered and threatened wildlife.

Change detection and land cover classification analysis can play an important role in making sure human life is able to safely and responsibly coexist with the rest of the planets inhabitants.

How do you support your environmental conservation project with remote sensing and geospatial analysis?

Posted in Geospatial Data, Remote Sensing | Tagged , , , , , , , , , , , , | Leave a comment