A Deep Learning Method Based on Two-Stage CNN Framework for Recognition of Chinese Reservoirs with Sentinel-2 Images

doi:10.3390/w14223755

	A Deep Learning Method Based on Two-Stage CNN Framework for Recognition of Chinese Reservoirs with Sentinel-2 Images
	Zhao, Guodongfang 1; Yao, Ping 1; Fu, Li 1; Zhang, Zhibin 1; Lu, Shanlong 2,3; Long, Tengfei 3
	2022-11-01
发表期刊	WATER
卷号	14 期号:22 页码:21
摘要	The development of effective and comprehensive methods for mapping and monitoring reservoirs is essential for the utilization of water resources and flood control. Remote sensing has the great advantages of broad spatial coverage and regular revisit to meet the demand of large-scale and long-term tasks of earth observation. Although there already exist some methods for coarse-grained identification of reservoirs at region-level in remote sensing images, it remains a challenge to recognize and localize reservoirs accurately with insufficiency of object details and samples annotated. This study focuses on the fine-grained identification and location of reservoirs with a two-stage CNN framework method, which is comprised of a coarse classification between aquatic and land areas of image patches and a fine detection of reservoirs in aquatic patches with precise geographical coordinates. Moreover, a NIR RCNN detection network is proposed to make use of the multi-spectral characteristics of Sentinel-2 images. To verify the effectiveness of our proposed method, we construct a reservoir and dam dataset of 36 Sentinel-2 images which are sampled in various provinces across China and annotated at the instance level by manual work. The experimental results in the test set show that the two-stage CNN method achieves an average recall of 80.83% nationwide, and the comparison between reservoirs recognized by the proposed model and those provided by the China Institute of Water Resources and Hydropower Research verifies that the model reaches a recall of about 90%. Both the indicator evaluation and visualization of identification results have shown the applicability of the proposed method to reservoir recognition in remote sensing images. Being the first attempt to make a fine-grained identification of reservoirs at the instance level, the two-stage CNN framework, which can automatically identify and localize reservoirs in remote sensing images precisely, shows the prospect to be a useful tool for large-scale and long-term reservoir monitoring.
关键词	two-stage CNN framework recognition of reservoirs remote sensing deep learning Sentinel-2 object detection
DOI	10.3390/w14223755
收录类别	SCI
语种	英语
资助项目	Chinese Academy of Sciences[XDA19020400] ; Chinese Academy of Sciences[XDA19090120]
WOS研究方向	Environmental Sciences & Ecology ; Water Resources
WOS类目	Environmental Sciences ; Water Resources
WOS记录号	WOS:000887775400001
出版者	MDPI
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20257
专题	中国科学院计算技术研究所期刊论文
通讯作者	Yao, Ping; Lu, Shanlong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100086, Peoples R China 2.Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100101, Peoples R China 3.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Guodongfang,Yao, Ping,Fu, Li,et al. A Deep Learning Method Based on Two-Stage CNN Framework for Recognition of Chinese Reservoirs with Sentinel-2 Images[J]. WATER,2022,14(22):21.
APA	Zhao, Guodongfang,Yao, Ping,Fu, Li,Zhang, Zhibin,Lu, Shanlong,&Long, Tengfei.(2022).A Deep Learning Method Based on Two-Stage CNN Framework for Recognition of Chinese Reservoirs with Sentinel-2 Images.WATER,14(22),21.
MLA	Zhao, Guodongfang,et al."A Deep Learning Method Based on Two-Stage CNN Framework for Recognition of Chinese Reservoirs with Sentinel-2 Images".WATER 14.22(2022):21.