Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives

doi:10.1007/s10462-017-9569-z

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives
	Wang, Kunfeng1 ; Gou, Chao1 ; Zheng, Nanning 2; Rehg, James M.3; Wang, Fei-Yue1,4
刊名	ARTIFICIAL INTELLIGENCE REVIEW
	2017-10-01
卷号	48 期号:3 页码:299-329
关键词	Visual Perception Complex Scenes Parallel Vision Acp Methodology Computer Graphics Image Synthesis
DOI	10.1007/s10462-017-9569-z
文献子类	Article
英文摘要	; In the study of image and vision computing, the generalization capability of an algorithm often determines whether it is able to work well in complex scenes. The goal of this review article is to survey the use of photorealistic image synthesis methods in addressing the problems of visual perception and understanding. Currently, the ACP Methodology comprising artificial systems, computational experiments, and parallel execution is playing an essential role in modeling and control of complex systems. This paper extends the ACP Methodology into the computer vision field, by proposing the concept and basic framework of Parallel Vision. In this paper, we first review previous works related to Parallel Vision, in terms of synthetic data generation and utilization. We detail the utility of synthetic data for feature analysis, object analysis, scene analysis, and other analyses. Then we propose the basic framework of Parallel Vision, which is composed of an ACP trilogy (artificial scenes, computational experiments, and parallel execution). We also present some in-depth thoughts and perspectives on Parallel Vision. This paper emphasizes the significance of synthetic data to vision system design and suggests a novel research methodology for perception and understanding of complex scenes.
WOS关键词	PEDESTRIAN DETECTION ; VIDEO SURVEILLANCE ; DOMAIN ADAPTATION ; CAMERA NETWORKS ; COMPUTER VISION ; VIRTUAL WORLDS ; RECOGNITION ; IMAGES ; ALGORITHMS ; MACHINES
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000412658700001
资助机构	National Natural Science Foundation of China(61533019 ; 71232006)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/20082]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Xi An Jiao Tong Univ, IAIR, Xian 710049, Shaanxi, Peoples R China 3.Georgia Inst Technol, Sch Interact Comp, Atlanta, GA 30332 USA 4.Natl Univ Def Technol, Res Ctr Computat Expt & Parallel Syst Tech, Changsha 410073, Hunan, Peoples R China
推荐引用方式 GB/T 7714	Wang, Kunfeng,Gou, Chao,Zheng, Nanning,et al. Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives[J]. ARTIFICIAL INTELLIGENCE REVIEW,2017,48(3):299-329.
APA	Wang, Kunfeng,Gou, Chao,Zheng, Nanning,Rehg, James M.,&Wang, Fei-Yue.(2017).Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives.ARTIFICIAL INTELLIGENCE REVIEW,48(3),299-329.
MLA	Wang, Kunfeng,et al."Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives".ARTIFICIAL INTELLIGENCE REVIEW 48.3(2017):299-329.