Deep images enhancement for turbid underwater images based on unsupervised learning

doi:10.1016/j.compag.2022.107372

	Deep images enhancement for turbid underwater images based on unsupervised learning
	Zhou, Wen-Hui 1; Zhu, Deng-Ming 1; Shi, Min 2; Li, Zhao-Xin 1; Duan, Ming 3; Wang, Zhao-Qi 1; Zhao, Guo-Liang 2; Zheng, Cheng-Dong 2
	2022-11-01
发表期刊	COMPUTERS AND ELECTRONICS IN AGRICULTURE
ISSN	0168-1699
卷号	202 页码:10
摘要	In agriculture, aquaculture technologies such as precise feeding, fish identification and fishing based on underwater machine vision all rely on the analysis of underwater images. However, due to the scatting and attenuation of the illumination in the real-world underwater environment, turbid underwater images are inevitably degraded, limiting their applicability in many vision tasks. In this paper, we present an unsupervised deep learning framework, called Underwater Loop Enhancement Network (ULENet), to improve the quality of turbid underwater images. We first propose an underwater dataset construction scheme and construct the dataset on which the network proposed above is trained. The underwater dataset contains images of three different scenes: lake and reservoir scene data (no label), pool scene data (weakly correlated label), and laboratory scene data (strongly correlated label). Then we propose a loop enhancement structure that uses the approximate candidates as labels and improves the visual quality of the image through the iterative training process. We formulate a new underwater visual perception loss function that evaluates the perceptual image quality based on its color, contrast, saturation and clarity. During the training process, a more realistic, higher -contrast, and clearer underwater image is gradually generated. Qualitative and quantitative evaluations show that the proposed method can effectively enhance image clarity. Moreover, the enhanced images are applied to several vision tasks to achieve better results, such as edge detection, key point matching, fish target detection and saliency prediction etc.
关键词	Image enhancement Visual perception Underwater dataset Deep learning
DOI	10.1016/j.compag.2022.107372
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China ; Scientific Research Instrument and Equipment Development Project of Chinese Academy of Sciences ; [2020YFB1710400] ; [YJKYYQ20190055]
WOS研究方向	Agriculture ; Computer Science
WOS类目	Agriculture, Multidisciplinary ; Computer Science, Interdisciplinary Applications
WOS记录号	WOS:000868790000004
出版者	ELSEVIER SCI LTD
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19767
专题	中国科学院计算技术研究所期刊论文
通讯作者	Zhu, Deng-Ming
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China 3.Chinese Acad Sci, Inst Hydrobiol, Wuhan 430072, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Wen-Hui,Zhu, Deng-Ming,Shi, Min,et al. Deep images enhancement for turbid underwater images based on unsupervised learning[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2022,202:10.
APA	Zhou, Wen-Hui.,Zhu, Deng-Ming.,Shi, Min.,Li, Zhao-Xin.,Duan, Ming.,...&Zheng, Cheng-Dong.(2022).Deep images enhancement for turbid underwater images based on unsupervised learning.COMPUTERS AND ELECTRONICS IN AGRICULTURE,202,10.
MLA	Zhou, Wen-Hui,et al."Deep images enhancement for turbid underwater images based on unsupervised learning".COMPUTERS AND ELECTRONICS IN AGRICULTURE 202(2022):10.