An Improved Deep Learning Approach for Retrieving Outfalls Into Rivers From UAS Imagery
文献类型:期刊论文
作者 | Huang, Yaohuan2,3; Wu, Chengbin2,3; Yang, Haijun1; Zhu, Haitao1; Chen, Mingxing2,3; Yang, Jie2,3 |
刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
出版日期 | 2021-09-30 |
页码 | 14 |
ISSN号 | 0196-2892 |
关键词 | Rivers Visualization Remote sensing Manuals Inspection Water resources Task analysis Deep learning digital surface model (DSM) faster region convolutional neural network (R-CNN) outfalls into river unmanned aircraft systems (UAS) imagery |
DOI | 10.1109/TGRS.2021.3113901 |
通讯作者 | Wu, Chengbin(wucb.19s@igsnrr.ac.cn) |
英文摘要 | Outfalls into rivers are the final gate of anthropogenic pollution flowing to receiving waters, which means that outfall surveys are significant to basin environmental protection and ecosystem health management. Unmanned aircraft systems (UAS) with high spatial resolution imagery have become important data for ongoing surveys of outfalls. However, outfalls retrieval from UAS imagery is inefficient to visual interpretation and a challenging task for traditional spectral-based and object-oriented classification methods given the problems of salt-and-pepper noise and scale selection. In this study, an improved geo-deep learning approach based on the faster region convolutional neural network (R-CNN) architecture (GDCNN-outfalls) is proposed for retrieving outfalls into rivers with UAS imagery. In the proposed method, three tactics--anchor size, region of interest (RoI), and hard negative mining--were adopted to optimize the benchmark Faster R-CNN application in outfalls retrieval. Meanwhile, a geo-classifier module with digital surface model (DSM) enhancement and a spatial activation function was integrated with the Faster R-CNN architecture to generate GDCNN-outfalls. The validation experiments indicated that GDCNN-outfalls improved the performance of Faster R-CNN in outfall retrieval by suppressing false positive (FPs) from 33.52% to 26.14% and increasing the F1 score from 0.72 to 0.75. The test results confirm the performance of GDCNN-outfalls with a recall of 79.3% and higher precision (48.4%) than that of Faster R-CNN (2.1%), also show the GDCNN-outfalls is ten times faster than visual interpretation. This study demonstrates that the combination of deep learning and UAS techniques can be a feasible solution to detect outfalls in outfall surveys. |
WOS关键词 | OBJECT DETECTION ; NEURAL-NETWORK ; WATER-QUALITY ; EXAMPLE ; PLUMES ; IMPACT |
资助项目 | National Natural Science Foundation of China[41822104] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19040402] ; National Key Research and Development Program of China[2017YFB0503005] ; National Science and Technology Major Project of China's High Resolution Earth Observation system[21-Y20B01-900119/22] |
WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000732766000001 |
资助机构 | National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; National Key Research and Development Program of China ; National Science and Technology Major Project of China's High Resolution Earth Observation system |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/168696] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Wu, Chengbin |
作者单位 | 1.Minist Ecol & Environm, Ctr Satellite Applicat Ecol & Environm, Beijing 100094, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 3.Univ Chinese Acad Sci, Coll Resource & Environm, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Huang, Yaohuan,Wu, Chengbin,Yang, Haijun,et al. An Improved Deep Learning Approach for Retrieving Outfalls Into Rivers From UAS Imagery[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2021:14. |
APA | Huang, Yaohuan,Wu, Chengbin,Yang, Haijun,Zhu, Haitao,Chen, Mingxing,&Yang, Jie.(2021).An Improved Deep Learning Approach for Retrieving Outfalls Into Rivers From UAS Imagery.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,14. |
MLA | Huang, Yaohuan,et al."An Improved Deep Learning Approach for Retrieving Outfalls Into Rivers From UAS Imagery".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021):14. |
入库方式: OAI收割
来源:地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。