Feature Selection and Mislabeled Waveform Correction for Water–Land Discrimination Using Airborne Infrared Laser

The discrimination of water–land waveforms is a critical step in the processing airborne topobathy LiDAR data. Waveform features, such as amplitudes infrared (IR) laser LiDAR, have been used identifying interfaces coastal waters through waveform clustering. However, using other IR full width at half maximum, area, width, and combinations different has not evaluated compared with methods. Furthermore, false alarms often occur when areas conducted because environmental factors. This study provides an optimal feature for by comparing performance features proposes dual-clustering method integrating K-means density-based spatial clustering applications noise algorithms to improve accuracy positions spot centers. proposed practical measurement Optech Coastal Zone Mapping Imaging LiDAR. Results show that amplitude among researched features. can correct mislabeled water or land reduce number 48% respect obtained traditional Water–land reach overall 99.730%. are recommended inland high accuracy, resolution, automation