Saliency Detection via Depth-Induced Cellular Automata on Light Field

doi:10.1109/TIP.2019.2942434

	Saliency Detection via Depth-Induced Cellular Automata on Light Field
	Yongri Piao 1; Xiao Li 1; Miao Zhang 2; Jingyi Yu3 ; Huchuan Lu 1
	2020
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
EISSN	1941-0042
卷号	29 页码:1879-1889
发表状态	已发表
DOI	10.1109/TIP.2019.2942434
摘要	Incorrect saliency detection such as false alarms and missed alarms may lead to potentially severe consequences in various application areas. Effective separation of salient objects in complex scenes is a major challenge in saliency detection. In this paper, we propose a new method for saliency detection on light field to improve the saliency detection in challenging scenes. We construct an object-guided depth map, which acts as an inducer to efficiently incorporate the relations among light field cues, by using abundant light field cues. Furthermore, we enforce spatial consistency by constructing an optimization model, named Depth-induced Cellular Automata (DCA), in which the saliency value of each superpixel is updated by exploiting the intrinsic relevance of its similar regions. Additionally, the proposed DCA model enables inaccurate saliency maps to achieve a high level of accuracy. We analyze our approach on one publicly available dataset. Experiments show the proposed method is robust to a wide range of challenging scenes and outperforms the state-of-the-art 2D/3D/4D (light-field) saliency detection approaches.
关键词	Saliency detection Image color analysis Automata Three-dimensional displays Two dimensional displays Visualization Computational modeling Saliency detection light field focusness cue depth cue depth-induced cellular automata (DCA) model
URL	查看原文
收录类别	SCI ; SCIE ; EI
语种	英语
资助项目	Fundamental Research Funds for the Central Universities[DUT19JC58]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000501324900017
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS关键词	VISUAL SALIENCY
原始文献类型	Article
来源库	IEEE
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/104516
专题	信息科学与技术学院信息科学与技术学院_PI研究组_虞晶怡组
作者单位	1.School of Information and Communication Engineering, Dalian University of Technology, Dalian, China 2.DUT-RU International School of Information Science & Engineering, Dalian University of Technology, Dalian, China 3.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Yongri Piao,Xiao Li,Miao Zhang,et al. Saliency Detection via Depth-Induced Cellular Automata on Light Field[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:1879-1889.
APA	Yongri Piao,Xiao Li,Miao Zhang,Jingyi Yu,&Huchuan Lu.(2020).Saliency Detection via Depth-Induced Cellular Automata on Light Field.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,1879-1889.
MLA	Yongri Piao,et al."Saliency Detection via Depth-Induced Cellular Automata on Light Field".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):1879-1889.