文献类型：期刊文献

英文题名：High resolution remote sensing recognition of elm sparse forest via deep-learning-based semantic segmentation

作者：Liu, Hao[1,2] Sun, Bin[1,2] Gao, Zhihai[1,2] Chen, Zhulin[1,3] Zhu, Zhongzheng[4]

第一作者：刘华;Liu, Hao

通信作者：Sun, B[1];Sun, B[2]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]NFGA, Key Lab Forestry Remote Sensing & Informat Syst, Beijing 100091, Peoples R China;[3]NFGA, Key Lab Forest Management & Growth Modelling, Beijing 100091, Peoples R China;[4]Chinese Acad Sci, Inst Tibetan Plateau Res, Natl Tibetan Plateau Data Ctr TPDC, State Key Lab Tibetan Plateau Earth Syst Sci Envir, Beijing 100101, Peoples R China

年份：2024

卷号：166

外文期刊名：ECOLOGICAL INDICATORS

收录：;EI(收录号：20243116799645);Scopus(收录号：2-s2.0-85199978502);WOS:【SCI-EXPANDED(收录号:WOS:001284665000001)】；

基金：This research was supported by the National Natural Science Foundation of China (42271407, 42001386) , the Fundamental Research Funds for the Central Non-profit Research Institution of CAF (grant number: CAFYBB2019ZB004) , and the special fund for Science and Technology Innovation Teams of Shanxi Province (202204051001010) . Special thanks to our annotation team members: Jiamin Wu, Yongjian Gu, Zhenting Sun, Xiangruo Chu, Junya Liu and Hao Liu.

语种：英文

外文关键词：Otingdag Sandy Land; Elm Sparse Forest; Gaofen-2; Semantic Segmentation; Deep Learning

摘要：Elm (Ulmus pumila L.) sparse forest plays an vital role in maintaining local ecological stability and security in the Otingdag Sandy Land area. Prior studies on elm canopy extraction have predominantly relied on manual parameter configuration, resulting in unsatisfactory levels of generalization. To meet the needs of high-precision and rapid recognition of elm sparse forests in large areas, this study proposed a recognition method for elm sparse forest that orients to high spatial resolution remote sensing imageries, using deep-learning-based semantic segmentation techniques. It can automatically learn features that are conducive to segmenting the canopy of elm trees, and retains good generalization ability on the Gaofen-2 imageries obtained in different regions. First, we constructed a dataset specialized for elm canopy semantic segmentation task, and annotated over 130,000 elm canopies based on Gaofen-2 imageries. In addition, we trained 7 deep-learning semantic segmentation model candidates. Among them, MANet showed the best performance, with its F1-score reaching 81.44%. Lastly, we applied edge detection to the elm canopy coverage area, and automatically extract the elm canopy. The proposed method can provide technical support for the investigation and monitoring of elm sparse forests, while facilitates local desertification prevention efforts in the entire Otingdag Sandy Region.