Improved Tree Segmentation Algorithm Based on Backpack-LiDAR Point Cloud

Abstract

For extracting tree structural data from LiDAR point clouds, individual tree segmentation is of great significance. Most individual tree segmentation algorithms miss segmentation and misrecognition, requiring manual post-processing. This study utilized a hierarchical approach known as segmentation based on hierarchical strategy (SHS) to improve individual tree segmentation. The tree point cloud was divided into the trunk layer and the canopy layer to carry out trunk detection and canopy segmentation, respectively. The effectiveness of SHS was evaluated on three mixed broadleaf forest plots. The segmentation efficacy of SHS was evaluated on three mixed broadleaf forest plots and compared with the point cloud segmentation algorithm (PCS) and the comparative shortest-path algorithm (CSP). In the three plots, SHS correctly identified all the trunk portion, had a recall (r) of 1, 0.98, and 1, a precision (p) of 1, and an overall segmentation rate (F) of 1, 0.99, and 1. CSP and PCS are less accurate than SHS. In terms of overall plots, SHS had 10%–15% higher F-scores than PCS and CSP. SHS extracted crown diameters with R2s of 0.91, 0.93, and 0.89 and RMSEs of 0.24 m, 0.23 m, and 0.30 m, outperforming CSP and PCS. Afterwards, we evaluate the three algorithms’ findings, examine the SHS algorithm’s parameters and constraints, and discuss the future directions of this research. This work offers an enhanced SHS that improves upon earlier research, addressing missed segmentation and misrecognition issues. It improves segmentation accuracy, individual tree segmentation, and provides both theoretical and data support for the LiDAR application in forest detection.