Evaluation of defogging: A real-world benchmark dataset, a new criterion and baselines

doi:10.1109/ICME.2019.00316

	Evaluation of defogging: A real-world benchmark dataset, a new criterion and baselines
	Zhao, Shiyu 1; Zhang, Lin 1; Huang, Shuaiyi2 ; Shen, Ying 1; Zhao, Shengjie 1; Yang, Yukai 3
	2019
会议录名称	2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME 2019
ISSN	1945788X
卷号	2019-July
页码	1840-1845
发表状态	已发表
DOI	10.1109/ICME.2019.00316
摘要	Modern defogging methods are able to achieve very comparable results whose differences are too subtle for people to qualitatively judge. On the other hand, existing quantitative evaluation methods are also not convincing due to a lack of proper datasets. In this work, we attempt to address these issues and establish a long-term lacking benchmark dataset, namely BeDDE (BEnchmark Dataset for Defogging Evaluation), for evaluating the performance of defogging algorithms. To our knowledge, BeDDE is the first real-world dataset comprising foggy images with their registered clear counterparts. Using BeDDE, we set up a new criterion for evaluating defogging methods where VSI, a full reference image quality assessment metric, is calculated and averaged on registered ROIs of all image pairs. The evaluation results of the proposed criterion correlate well with human judgements. 10 state-of-the-art defogging methods are evaluated as baselines on BeDDE. BeDDE is available online. © 2019 IEEE.
会议地点	Shanghai, China
会议日期	8-12 July 2019
URL	查看原文
收录类别	EI ; CPCI-S ; CPCI
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000501820600308
出版者	IEEE Computer Society
EI入藏号	20193407349190
EI主题词	Benchmarking
EI分类号	Petroleum Deposits : Development Operations:512.1.2
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/89391
专题	信息科学与技术学院_硕士生
通讯作者	Zhang, Lin; Shen, Ying
作者单位	1.School of Software Engineering, Tongji University, Shanghai, China 2.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 3.Department of Statistics, Uppsala University, Uppsala, Sweden
推荐引用方式 GB/T 7714	Zhao, Shiyu,Zhang, Lin,Huang, Shuaiyi,et al. Evaluation of defogging: A real-world benchmark dataset, a new criterion and baselines[C]:IEEE Computer Society,2019:1840-1845.