文献类型：期刊文献

英文题名：VrsNet- density map prediction network for individual tree detection and counting from UAV images

作者：Luo, Taige[1] Gao, Wei[1] Belotserkovsky, Alexei[3] Nedzved, Alexander[4] Deng, Weijie[5] Ye, Qiaolin[1,6,7,8] Fu, Liyong[2] Chen, Qiao[2] Ma, Wenjun[2] Xu, Sheng[1]

第一作者：Luo, Taige

通信作者：Xu, S[1]

机构：[1]Nanjing Forestry Univ, Coll Informat Sci & Technol & Artificial Intellige, Nanjing 210037, Jiangsu, Peoples R China;[2]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[3]Problems Natl Acad Sci Belarus, United Inst Informat, Minsk 220012, BELARUS;[4]Belarusian State Univ, Minsk 220030, BELARUS;[5]Nanjing Forestry Univ, Coll Econ & Management, Nanjing 210037, Jiangsu, Peoples R China;[6]Nanjing Forestry Univ, State Key Lab Tree Genet & Breeding, Nanjing 210037, Peoples R China;[7]Nanjing Forestry Univ, Coinnovat Ctr Sustainable Forestry Southern China, Educ Dept China, Key Lab Tree Genet & Biotechnol, Nanjing 210037, Jiangsu, Peoples R China;[8]Nanjing Forestry Univ, Key Lab Tree Genet & Silvicultural Sci Jiangsu Pro, Nanjing 210037, Jiangsu, Peoples R China

年份：2024

卷号：130

外文期刊名：INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION

收录：;EI(收录号：20240094684);Scopus(收录号：2-s2.0-85194764382);WOS:【SCI-EXPANDED(收录号:WOS:001297186000001)】；

基金：This research is supported in part by the Fundamental Research Funds for the Central Nonprofit Research Institution of CAF (CAFYBB2022ZB002) , and in party by National Natural Science Foun-dation of China (NO. 62102184, NO. 32371877)

语种：英文

外文关键词：Vegetation mapping; Remote sensing; Semi-supervised learning; Object detection; Tree segmentation; Tree counting; Density map

摘要：Individual tree detection and counting in unmanned aerial vehicle (UAV) imagery constitute a vital and practical research field. Vegetation remote sensing captures large-scale trees characterized by complex textures, significant growth variations, and high species similarity within the vegetation, which presents significant challenges for annotation and detection. Existing methods based on bounding boxes have struggled to convey semantics information about tree crowns. This paper proposes a novel deep learning network called VrsNet based on the density map information. The proposed work pioneers the segmentation and counting application by utilizing the semantic information of Gaussian contour. Besides, we sample and create the UAV vegetation remote sensing density dataset TreeFsc for experiments. In quantitative comparison across multiple datasets, the proposed method demonstrates high performance, with a 3.45 increase in MAE and a 4.75 increase in RMSE. Experiments demonstrate superior cross -region, cross -scale, and cross -species target detection capabilities of the proposed approach compared with the existing object detection methods. Our code and dataset are available at: https://github.com/luotiger123/VrsNet/tree/main/VrsNet.