Identifying Significant Environmental Features Using Feature Recognition.

摘要

The Department of Environmental Analysis at the Kentucky Transportation Cabinet has expressed an interest in feature recognition capability because it may help analysts identify environmentally sensitive features in the landscape, including those relating to historic preservation, archaeology, endangered species habitat, and geology. LIDAR Analyst and Feature Analyst are a pair of geo-processing software packages that have been developed by Textron Systems. Using this software, users can use LIDAR data to identify finely-scaled user-specified features. The software’s automated feature extraction saves time that might otherwise be spent manually analyzing images and digitizing features. This report explores the capabilities and accuracy of this software by using LIDAR data to identify sinkholes throughout a small area in Kentucky. This report also discusses an alternative LIDAR-based geoprocessing methodology developed by the Kentucky Geological Society. The method relies on ArcGIS and Python scripting to identify sinkholes. The feasibility and applicability of these methodologies are compared, the workflow for each method is outlined, and the capabilities and limitations of each are noted. Sample results—the identification of sinkholes—from each methodology are presented. The research team found the batch processing capability built into LIDAR and Feature Analyst adequate and beneficial for smaller projects, such as projects that prioritize the extraction of buildings, trees, and forest regions.