文献类型：期刊文献

英文题名：YOLOTree-Individual Tree Spatial Positioning and Crown Volume Calculation Using UAV-RGB Imagery and LiDAR Data

作者：Luo, Taige[1] Rao, Shuyu[1] Ma, Wenjun[2] Song, Qingyang[1] Cao, Zhaodong[1] Zhang, Huacheng[1] Xie, Junru[1] Wen, Xudong[1] Gao, Wei[1] Chen, Qiao[3] Yun, Jiayan[4] Wu, Dongyang[1]

第一作者：Luo, Taige

通信作者：Chen, Q[1];Yun, JY[2]

机构：[1]Nanjing Forestry Univ, Coll Informat Sci & Technol & Artificial Intellige, Nanjing 210037, Peoples R China;[2]Chinese Acad Forestry, Res Inst Forestry, State Key Lab Tree Genet & Breeding, Key Lab Tree Breeding & Cultivat,State Forestry Ad, Beijing 100091, Peoples R China;[3]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[4]Tongji Univ, Coll Architecture & Urban Planning, Dept Landscape Architecture, Shanghai 200092, Peoples R China

年份：2024

卷号：15

期号：8

外文期刊名：FORESTS

收录：;EI(收录号：20243616970980);Scopus(收录号：2-s2.0-85202660827);WOS:【SCI-EXPANDED(收录号:WOS:001304682800001)】；

基金：This research was funded by Fundamental Research Funds for the Central Nonprofit Research Institution of CAF (CAFYBB2022ZB002) and in part by China Scholarship Council (CSC) funded overseas cooperation projects, innovative talents international cooperation training projects, No. 202306260335, and in part by Ministry of Education Humanities and Social Sciences Youth Fund Project, No. 23YJC760149.

语种：英文

外文关键词：remote sensing; unmanned aerial vehicle; object detection; individual tree; crown volume; deep learning

摘要：Individual tree canopy extraction plays an important role in downstream studies such as plant phenotyping, panoptic segmentation and growth monitoring. Canopy volume calculation is an essential part of these studies. However, existing volume calculation methods based on LiDAR or based on UAV-RGB imagery cannot balance accuracy and real-time performance. Thus, we propose a two-step individual tree volumetric modeling method: first, we use RGB remote sensing images to obtain the crown volume information, and then we use spatially aligned point cloud data to obtain the height information to automate the calculation of the crown volume. After introducing the point cloud information, our method outperforms the RGB image-only based method in 62.5% of the volumetric accuracy. The AbsoluteError of tree crown volume is decreased by 8.304. Compared with the traditional 2.5D volume calculation method using cloud point data only, the proposed method is decreased by 93.306. Our method also achieves fast extraction of vegetation over a large area. Moreover, the proposed YOLOTree model is more comprehensive than the existing YOLO series in tree detection, with 0.81% improvement in precision, and ranks second in the whole series for mAP50-95 metrics. We sample and open-source the TreeLD dataset to contribute to research migration.