Benggang segmentation via deep exchanging of digital orthophoto map and digital surface model features  

作　　者：Shengyu Shen Jiasheng Chen Dongbing Cheng Honghu Liu Tong Zhang 

机构地区：[1]Department of Soil and Water Conservation,Changjiang River Scientific Research Institute of Changjiang Water Resources Commission,Wuhan,430010,China [2]Research Center on Mountain Torrent&Geologic Disaster Prevention,Ministry of Water Resources,Wuhan,430010,China [3]State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing(LIESMARS),Wuhan University,Wuhan,430079,China

出　　处：《International Soil and Water Conservation Research》2024年第3期589-599,共11页国际水土保持研究（英文）

基　　金：funded by Key Research and Development Program of Hubei Province,China under grant 2021BAA186;the National Natural Science Foundation of China under grant number 41601298.

摘　　要：Benggang is a typical fragmented erosional landscape in southern and southeastern China,posing sig-nificant risk to the local residents and economic development.Therefore,an efficient and accurate fine-grained segmentation method is crucial for monitoring the Benggang areas.In this paper,we propose a deep learning-based automatic segmentation method for Benggang by integrating high-resolution Digital Orthophoto Map(DOM)and Digital Surface Model(DSM)data.The DSM data is used to extract slope maps,aiming to capture primary morphological features.The proposed method consists of a dual-stream convolutional encoder-decoder network in which multiple cascaded convolutional layers and a skip connection scheme are used to extract morphological and visual features of the Benggang areas.The rich discriminative information in the DOM and slope data is fused by a channel exchanging mechanism that dynamically exchanges the most discriminative features from either the DOM or DSM stream ac-cording to their importance at the channel level.Evaluation experiments were conducted on a chal-lenging dataset collected from Guangdong Province,China,and the results show that the proposed channel exchanging network based deep fusion method achieves 84.62%IoU in Benggang segmentation,outperforming several existing unimodal or multimodal baselines.The proposed multimodal segmen-tation method greatly improves the efficiency of large-scale discovery of Benggang,and thus is important for the management and restoration of Benggang in southern and southeastern China,as well as the monitoring of other similar erosional landscapes.

关 键 词：Benggang segmentation Deep fusion Channel exchanging DOM DSM 

分 类 号：S15[农业科学—土壤学]