文献类型：期刊文献

英文题名：BASNet: Burned Area Segmentation Network for Real-Time Detection of Damage Maps in Remote Sensing Images

作者：Bo, Weihao[1] Liu, Jie[1] Fan, Xijian[1] Tjahjadi, Tardi[2] Ye, Qiaolin[1] Fu, Liyong[3]

第一作者：Bo, Weihao

通信作者：Fan, XJ[1]

机构：[1]Coll Informat Sci & Technol, Nanjing 210037, Peoples R China;[2]Univ Warwick, Sch Engn, Coventry CV4 7AL, W Midlands, England;[3]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China

年份：2022

卷号：60

外文期刊名：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

收录：;EI(收录号：20223412601442);Scopus(收录号：2-s2.0-85136026817);WOS:【SCI-EXPANDED(收录号:WOS:000844159700010)】；

基金：This work was supported in part by the Project of Construction of UAV Patrol Monitoring System For Forest Fire Prevention in Chongli District of Zhangjiakou under Grant DA2020001; in part by the National Natural Science Foundation of China under Grant 61902187 and Grant 62072246; and in part by the Joint Fund of Science and Technology Department of Liaoning Province and State Key Laboratory of Robotics, China, under Grant 2020-KF-22-04.

语种：英文

外文关键词：Image segmentation; Semantics; Vegetation mapping; Optical imaging; Feature extraction; Autonomous aerial vehicles; Satellites; Burned area segmentation (BAS); convolutional neural network (CNN); forest fire monitoring; salient object detection (SOD)

摘要：Since remote sensing images of post-fire vegetation are characterized by high resolution, multiple interferences, and high similarities between the background and the target area, it is difficult for existing methods to detect and segment the burned area in these images with sufficient speed and accuracy. In this article, we apply salient object detection (SOD) to burned area segmentation (BAS), the first time this has been done, and propose an efficient burned area segmentation network (BASNet) to improve the performance of unmanned aerial vehicle (UAV) high-resolution image segmentation. BASNet comprises positioning module and refinement module. The positioning module efficiently extracts high-level semantic features and general contextual information via global average pooling layer and convolutional block (CB) to determine the coarse location of the salient region. The refinement module adopts the CB attention module to effectively discriminate the spatial location of objects. In addition, to effectively combine edge information with spatial location information in the lower layer of the network and the high-level semantic information in the deeper layer, we design the residual fusion module to perform feature fusion by level to obtain the prediction results of the network. Extensive experiments on two UAV datasets collected from Chongli in China and Andong in South Korea, demonstrate that our proposed BASNet significantly outperforms the state-of-the-art SOD methods quantitatively and qualitatively. BASNet also achieves a promising prediction speed for processing high-resolution UAV images, thus providing wide-ranging applicability in post-disaster monitoring and management.