文献类型：期刊文献

英文题名：Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM

作者：Wang, Jiansen[1,2] Zhang, Huaiqing[1,2] Liu, Yang[1,2] Zhang, Huacong[1,2,3] Zheng, Dongping[4]

第一作者：Wang, Jiansen

通信作者：Zhang, HQ[1];Zhang, HQ[2]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]Natl Forestry & Grassland Adm, Key Lab Forestry Remote Sensing & Informat Syst, Beijing 100091, Peoples R China;[3]Chinese Acad Forestry, Expt Ctr Subtrop Forestry, Xinyu 336600, Peoples R China;[4]Univ Hawaii Manoa, Dept Language Studies 2, 1890 East West Rd, Honolulu, HI 96822 USA

年份：2024

卷号：16

期号：2

外文期刊名：REMOTE SENSING

收录：;EI(收录号：20240515459982);Scopus(收录号：2-s2.0-85183324838);WOS:【SCI-EXPANDED(收录号:WOS:001151341800001)】；

基金：We are grateful to Jiangping Long, Central South University of Forestry and Technology, for providing supplementary data of the Huangfengqiao Forest Farm.

语种：英文

外文关键词：YOLOv5; individual tree detection; planted forests; Chinese fir; deformable convolution; attention mechanism

摘要：Achieving the accurate and efficient monitoring of forests at the tree level can provide detailed information for precise and scientific forest management. However, the detection of individual trees under planted forests characterized by dense distribution, serious overlap, and complicated background information is still a challenge. A new deep learning network, YOLO-DCAM, has been developed to effectively promote individual tree detection amidst complex scenes. The YOLO-DCAM is constructed by leveraging the YOLOv5 network as the basis and further enhancing the network's capability of extracting features by reasonably incorporating deformable convolutional layers into the backbone. Additionally, an efficient multi-scale attention module is integrated into the neck to enable the network to prioritize the tree crown features and reduce the interference of background information. The combination of these two modules can greatly enhance detection performance. The YOLO-DCAM achieved an impressive performance for the detection of Chinese fir instances within a comprehensive dataset comprising 978 images across four typical planted forest scenes, with model evaluation metrics of precision (96.1%), recall (93.0%), F1-score (94.5%), and AP@0.5 (97.3%), respectively. The comparative test showed that YOLO-DCAM has a good balance between model accuracy and efficiency compared with YOLOv5 and advanced detection models. Specifically, the precision increased by 2.6%, recall increased by 1.6%, F1-score increased by 2.1%, and AP@0.5 increased by 1.4% compared to YOLOv5. Across three supplementary plots, YOLO-DCAM consistently demonstrates strong robustness. These results illustrate the effectiveness of YOLO-DCAM for detecting individual trees in complex plantation environments. This study can serve as a reference for utilizing UAV-based RGB imagery to precisely detect individual trees, offering valuable implications for forest practical applications.