Issue link: https://read.dmtmag.com/i/46658
Increase Automation and Accuracy of Remote-Sensing Feature Extraction A WORLD OF INFORMATION T BY KIRK BENELL oday's geospatial analysts have a large array of tools and technologies available to rapidly and efficiently access, prepare and exploit remotely sensed information. However, they're increasingly unable to keep up with the large volumes of available information and the ever-increasing demands for extracted information. As a result, a different approach is needed to increase analytical efficiency and accuracy. The key to a new level of geospatial exploitation accuracy and efficiency is through a holistic approach that lever- ages the capabilities available across the entire geospatial domain. Modern information infrastructures now make it possible to access data from different sensor modalities, retrieve historical data from geodatabases and lever- age existing knowledge of an area under observation. It's through such data fusion environments that new levels of accuracy, timeliness and automation are possible, but current tool and data offerings still are focused on specific domains, trying to squeeze out incremental gains while analysts struggle with overwhelming information demands. Tools must break out of modality-bounded silos to deliver a unified, fully integrated exploitation ecosystem that enables rapid and accurate information extraction. Kirk Benell is the chief technology officer for ITT Visual Information Solutions (ITT VIS), developers of ENVI image-analysis and E3De LIDAR data-analysis software; e-mail: kirk@ittvis.com, Web: www.ittvis.com. 12 Modality Segmentation Most current application toolsets and data offerings all focus on a single-sensor modality: imagery tools for imagery; LIDAR tools for LIDAR datasets; radar tools for synthetic-aperture radar (SAR) data. This isn't surprising, given that these fields evolved around the methods used to capture data. The sensor developers needed tools to prepare and exploit collected data. But as the technology and sensor capabili- ties advanced, so did the tools available to each modality. Higher accuracy and greater information extraction was possible at a steady rate, meeting the information needs of organizations. GEO W ORLD / OCT O BE R 2O11 LIDAR data were incorporated with a multispectral image to help with building extraction in an area where building and ground-surface materials have a similar composition. Although the capabilities and derived products from each modality moved forward at a steady rate, the use of multi-modality data sources in an exploitation process historically was rare and often confined to experimental activities. The data, tools and expertise were segmented along modalities. Segmented operational tasking prevented collec- tion over a common area with multi-modality sensors difficult to coordinate. The only use of multi-modality information might occur at the decision makers' level, based on derived information products, well past the exploitation phase of information extraction. Breaking Down Modality Demarcation Today's landscape is changing. Decision makers are realizing the limitations of each sensor type and the value of combining modalities into a single operational environment. In addition, technology has evolved to enable the deployment of multi-modality sensor packages that can perform coordinated sen- sor collects. Policy, need and technical capability are converging to support multi-modality data collection. As with all technologies, the evolution of sensor packages has made it possible to support the deploy- ment, tasking and collection of multiple modalities in a single sensor package. Space and power requirements continue to shrink through advances in miniaturization. Increased storage capabilities and efficient com- munication protocols have enabled rapid data access. Combined with modern deployment models (e.g., unmanned aircraft operations) and the availability of multiple-modality platforms, common-collect datasets are becoming a reality for geospatial analysts. Besides increased data availability through the deployment of multi-modality sensor platforms,