From motion patterns to visual concepts for event analysis in dynamic scenes

CASIA OpenIR > 09年以前成果

	From motion patterns to visual concepts for event analysis in dynamic scenes
	Xin, L; Tan, TN; Narayanan, PJ; Nayar, SK; Shum, HY
发表期刊	COMPUTER VISION - ACCV 2006, PT I
	2006
卷号	3851 页码:826-835
文章类型	Article
摘要	The analysis of events in dynamic scenes has become an important and challenging problem increasingly in recent years. Events can be considered as obvious changes of important features with semantic meanings. From this viewpoint, the fundamental task of events analysis is to extract semantically meaningful changes and associate all of these basic motion patterns and changes with relevant visual concepts of moving objects in dynamic scenes. In this paper, we propose a method to extract lower level motion patterns and associate them with visual concepts respectively in a well-defined structure. Furthermore we also analyze latent spatial-temporal relationships among these basic visual concepts for event modeling and analysis. Finally, we present experimental results which prove the effectiveness of our approach on some realworld videos of dynamic scenes.
WOS标题词	Science & Technology ; Technology
关键词[WOS]	IMAGE SEQUENCES ; MARKOV-MODELS ; RECOGNITION
收录类别	ISTP ; SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:000235772300083
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/9246
专题	09年以前成果
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Xin, L,Tan, TN,Narayanan, PJ,et al. From motion patterns to visual concepts for event analysis in dynamic scenes[J]. COMPUTER VISION - ACCV 2006, PT I,2006,3851:826-835.
APA	Xin, L,Tan, TN,Narayanan, PJ,Nayar, SK,&Shum, HY.(2006).From motion patterns to visual concepts for event analysis in dynamic scenes.COMPUTER VISION - ACCV 2006, PT I,3851,826-835.
MLA	Xin, L,et al."From motion patterns to visual concepts for event analysis in dynamic scenes".COMPUTER VISION - ACCV 2006, PT I 3851(2006):826-835.