Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

• Published in: Forests Vol. 10; no. 9; p. 793
• Main Authors: Wang, Jiamin, Chen, Xinxin, Cao, Lin, An, Feng, Chen, Bangqian, Xue, Lianfeng, Yun, Ting
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 11.09.2019
• Subjects: Algorithms; Artificial neural networks; China; clones; Cloning; Data collection; Deep learning; Hevea brasiliensis; Hurricanes; Image segmentation; Inspection; Lasers; leaves; Lidar; Machine learning; Morphology; Natural disturbance; Neural networks; Object recognition; Rubber; Rubber trees; Training; tree crown; tree trunk; Trees; Typhoons; Wavelet transforms; China; Hainan Island

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of differe...