Instance recognition of street trees from urban point clouds using a three-stage neural network

Mapping Carbon Stock of Individual Street Trees Using Lidar-Camera Fusion-Based Mobile Mapping System

“…Detecting individual street trees in the point cloud is essential, as their structural parameters are vital for carbon stock estimation. Conventional methods for extracting individual trees from point clouds remain indispensable (Ning et al, 2019;Zhong et al, 2017), but recent DL-based methods have exhibited remarkable performance in segmenting individual trees from point clouds (Jiang et al, 2023;Luo et al, 2021). The practical use of DL models necessitates the generation of a training dataset tailored to the target site, leading to an increase in the volume of required training data across diverse urban scenarios on a city scale.…”