Automatic Extraction of Urban Features from Terrestrial LIDAR Systems

The U.S. Army requires automated feature extraction (AFE) software for collecting very high-resolution 3D urban features from terrestrial LIDAR data to support the ground-based Warfighter operating in the urban battlespace. Advanced vehicle-mounted and man-portable terrestrial Light Imaging and Range Detection (LIDAR) systems capture accurate 3D measurements of the urban environment with spatial resolutions on the order of 5 centimeters or less [Blais, 2004]. The 3D imaging capability of these systems is negated, however, by a lack of commercial software tools capable of exploiting terrestrial LIDAR datasets [Shiode 2001]. Current approaches for creating high-resolution 3D urban models are expensive requiring thousands of man-hours to digitize feature geometries, assign textures to features and attribute features. The lack of robust AFE software tools for collecting geospecific urban features from terrestrial LIDAR systems directly impacts applications for facility reconnaissance, special operations planning and urban warfare decision-making. Visual Learning Systems, Inc. (VLS) has developed a LIDAR AFE system capable of extracting over 1,000 buildings per minute as 3D Shapefiles from airborne LIDAR. VLS' proven capability in developing commercial AFE software tools, and prior research experience with LIDAR, provides the Army with a proven partner for developing a 3D AFE solution for advanced terrestrial LIDAR systems.