From Event: SPIE Defense + Commercial Sensing, 2019
Data from the Optech Titan airborne laser scanner were collected over Monterey, CA, in three wavelengths (532 nm, 1064 nm, and 1550 nm), in October 2016, by the National Center for Airborne LiDAR Mapping (NCALM). Lidar waveform data at 532 nm from the Optech Titan were analyzed for data collected over the forested area at the Pont Lobos State Park. Standard point cloud processing was done using LAStools. Waveform data were converted into pseudo “hypercubes” in order to facilitate use of the analysis structures used for hyperspectral imagery. Analysis approaches used were ENVI classification tools such as Support Vector Machines (SVM), Spectral Angle Mapper (SAM), Maximum Likelihood, and K-means to classify returns. Through the use of this analog to hyperspectral data analysis to classify vegetation and terrain, the results are that, by using the Support Vector Machines with full waveform data, we can successfully improve low vegetation classifiers by 40%, and differentiate tree types (Pine/Cypress) at 40–60% accuracy.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Richard C. Olsen, Andrew S. Davis, and Jeremy P. Metcalf, "Analysis and exploitation of lidar waveform data," Proc. SPIE 11005, Laser Radar Technology and Applications XXIV, 110050M (Presented at SPIE Defense + Commercial Sensing: April 17, 2019; Published: 2 May 2019); https://doi.org/10.1117/12.2519188.