Coarse-to-fine segmentation of individual street trees from side-view point clouds

• Published in: Urban forestry & urban greening 2023-11, Vol.89, p.128097, Article 128097
• Main Authors: Li, Qiujie, Yan, Yu, Li, Weizheng
• Format: Article
• Language: English
• Subjects: Coarse-to-fine segmentation; Individual tree segmentation; Overlapping tree segmentation; Point cloud instance segmentation; Side-view point cloud
• ISSN: 1618-8667; 1610-8167
• DOI: 10.1016/j.ufug.2023.128097

Segmenting individual street trees from a street side-view point cloud is the first and key step of obtaining a street tree inventory. Using the classification-segmentation framework for individual tree segmentation makes tree detection simple and accurate, but segmenting overlapping trees is still challenging. To more accurately segment overlapping trees, a coarse-to-fine method for segmenting individual street trees from a side-view point cloud is proposed in this paper. Following the classification-segmentation framework, the tree points are first detected from the side-view street point cloud by a pointwise classifier fused from 13 local geometric features and then trained using random forest (RF). Second, the tree proposals are obtained by density-based spatial clustering of applications with noise (DBSCAN) clustering and detection error filtering. Third, the overlapping tree proposals are recognized by trunk identification, and the single tree proposals are directly output as individual trees. Fourth, the overlapping trees are roughly divided into individual tree proposals through vertical planes. Finally, individual trees with optimized contours are obtained by iteratively using DBSCAN clustering and k-nearest neighbor (k-NN) classification. The side-view point cloud of a 290 m-long urban street containing 77 street trees is captured by a hand-held mobile ZEB Horizon laser scanner. The tree detection attained an F1 score of 0.9916 with a precision of 0.9989 and a recall of 0.9864. For individual tree segmentation, the F1 score was 0.9745 with a precision of 0.9672 and a recall of 0.9819. Compared to two current classification-segmentation methods, the overlapping tree segmentation F1 scores were increased by 0.0914 and 0.0617, respectively. The proposed method can be applied to tree parameter extraction, which is an important urban forest inventory task and is crucial for urban forest management. In our experiment, the root mean squared error (RMSE) of the trunk diameter at breast height (DBH) estimation was 0.8485 cm.