The Analysis of Object-based Point Clouds Features Using Airborne Waveform Lidar Data

Full-waveform lidar system records the received signals continuously for analysis. As it provides more information than the conventional pulsed lidar, the waveform lidar plays an important role in land cover classification as well as object reconstruction. The objective of this research is to analyze the features of grouped full-waveform lidar point clouds. The two major works are segmentation and feature analysis. Segmentation uses a 3-D region growing technique to merge the neighboring points within a certain distance. After segmentation, the features of each object are calculated to detect the building regions. An object’s features include geometric, waveform and statistical features. The test data is acquired by Riegl Q680i and is located in Tainan, Taiwan. The point density is 10 pts/m. The experimental result indicates that the proposed method may detect the buildings effectively.