Classification in LIDAR data is the process of determining points on terrain types and objects, often with the goal of determining land use and/or building footprints. In this paper we endeavor to classify terrain types and objects at a high level of detail in a complex scene that includes buildings, forested areas, and steep hillsides. Our object classes include buildings, building rooftop structures, forest trees, landscape trees, landscape bushes, cars, light posts of varying sizes, fences, paved surfaces, and grass. Our classification method of choice is a Random Forest, but we also investigate other machine learning methods including K-Nearest Neightbors and Linear Discriminant Analysis. We evaluate the effectiveness of the algorithms for accuracy, required training sample size, and runtime.
William F. Basener and Abigail Basener, "Classification and identification of small objects in complex urban-forested LIDAR data using machine learning," Proc. SPIE 10191, Laser Radar Technology and Applications XXII, 101910F (Presented at SPIE Defense + Security: April 12, 2017; Published: 5 May 2017); https://doi.org/10.1117/12.2264641.
Conference Presentations are recordings of oral presentations given at SPIE conferences and published as part of the conference proceedings. They include the speaker's narration along with a video recording of the presentation slides and animations. Many conference presentations also include full-text papers. Search and browse our growing collection of more than 14,000 conference presentations, including many plenary and keynote presentations.