Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas

doi:10.1080/01431161.2019.1706009

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas
	Cheng, Bo 2; Liang, Chenbin 2,3; Liu, Xunan 4; Liu, Yueming 1,2; Ma, Xiaoxiao 2; Wang, Guizhou 2
刊名	INTERNATIONAL JOURNAL OF REMOTE SENSING
	2020-05-02
卷号	41 期号:9 页码:3575-3591
ISSN号	0143-1161
DOI	10.1080/01431161.2019.1706009
通讯作者	Liang, Chenbin(liangcb@radi.ac.cn)
英文摘要	Recently, moderate-resolution remote sensing images have been widely used in extracting coastal aquaculture areas that are usually used to obtain marine fishery resources. However, in moderate-resolution remote sensing images, the aquaculture areas destroyed by storm-tide are hard to be observed. In order to get information of coastal aquaculture areas quickly and accurately, to help the scientific management and the planning of aquaculture resources and to meet the needs of disaster emergency response, it is imperative to extract aquaculture areas based on high-resolution remote sensing images. However, as the spatial resolution increases, there are many disadvantages that traditional pixel-level classification methods bring about, for example, the sediments and some floatage on the water surface are easy to be mistaken as aquaculture areas. In view of these problems, we proposed a novel Semantic Segmentation Network, named Hybrid Dilated Convolution U-Net (HDCUNet), which combines U-Net and Hybrid Dilated Convolution (HDC) to further expend receptive field and prevent the 'gridding' problem simultaneously. In this paper, we chose Gaofen-2 images as experimental data to extract aquaculture areas, and the Precisions and Recalls of two types of aquaculture areas are both above 95% and the overall accuracy reaches up to 99.16%. Besides, we compared the extraction accuracy with other four methods: FCN-8s, SegNet, U-Net and Threshold Segmentation (TS) to analyse the extraction effect and verify the validity of HDCUNet.
资助项目	Institute of Remote Sensing and Digital Earth Chinese Academy of Science (RADI) through the National Natural Science Foundation of China[61731022] ; National Marine Hazard Mitigation Service (NMHMS)
WOS研究方向	Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	TAYLOR & FRANCIS LTD
WOS记录号	WOS:000506454200003
资助机构	Institute of Remote Sensing and Digital Earth Chinese Academy of Science (RADI) through the National Natural Science Foundation of China ; National Marine Hazard Mitigation Service (NMHMS)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/29527]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Liang, Chenbin
作者单位	1.Inst Geog Sci & Nat Resource Res, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 4.Natl Marine Hazard Mitigat Serv, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Bo,Liang, Chenbin,Liu, Xunan,et al. Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas[J]. INTERNATIONAL JOURNAL OF REMOTE SENSING,2020,41(9):3575-3591.
APA	Cheng, Bo,Liang, Chenbin,Liu, Xunan,Liu, Yueming,Ma, Xiaoxiao,&Wang, Guizhou.(2020).Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas.INTERNATIONAL JOURNAL OF REMOTE SENSING,41(9),3575-3591.
MLA	Cheng, Bo,et al."Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas".INTERNATIONAL JOURNAL OF REMOTE SENSING 41.9(2020):3575-3591.