RepDDNet:a fast and accurate deforestation detection model with high-resolution remote sensing image

作     者：Zhipan Wang Zhongwu Wang Dongmei Yan Zewen Mo Hua Zhang Qingling Zhang 

作者机构：Shenzhen Key Laboratory of Intelligent Microsatellite ConstellationSun Yat-sen UniversityShenzhenPeople’s Republic of China Land Satellite Remote Sensing Application CenterMinistry of Natural ResourcesBeijingPeople’s Republic of China Aerospace Information Research InstituteChinese Academy of SciencesBeijingPeople’s Republic of China Changsha University of Science&TechnologyChangshaPeople’s Republic of China 

出 版 物：《International Journal of Digital Earth》 (国际数字地球学报（英文）)

年 卷 期：2023年第16卷第1期

页      面：2013-2033页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理] 

基　　金：supported by the Shenzhen Science and Technology Innovation Project(No.ZDSYS20210623091808026) supported in part by the National Natural Science Foundation of China(General Program,No.42071351) the National Key Research and Development Program of China(No.2020YFA0608501) the Chongqing Science and Technology Bureau technology innovation and application development special(cstc2021jscx-gksb0116) 

主　　题：Carbon neutral deforestation detection high-resolution remote sensing image deep learning reparameterization 

摘      要：Forest is the largest carbon reservoir and carbon absorber on ***,mapping forest cover change accurately is of great significance to achieving the global carbon neutrality *** forest change information could be acquired by deep learning methods using high-resolution remote sensing ***,deforestation detection based on deep learning on a large-scale region with high-resolution images required huge computational ***,there was an urgent need for a fast and accurate deforestation detection *** this study,we proposed an interesting but effective re-parameterization deforestation detection model,named *** other existing models designed for deforestation detection,the main feature of RepDDNet was its decoupling feature,which means that it allowed the multi-branch structure in the training stages to be converted into a plain structure in the inference stage,thus the computation efficiency can be significantly improved in the inference stage while maintaining the accuracy unchanged.A large-scale experiment was carried out in Ankang city with 2-meter high-resolution remote sensing images(the total area of it was over 20,000 square kilometers),and the result indicated that the model computation efficiency could be improved by nearly 30%compared with the model without ***,compared with other lightweight models,RepDDNet also displayed a trade-off between accuracy and computation efficiency.