M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling

	M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling
	Zhang, Tianzhu1,2 ; Liu, Si 1,2; Xu, Changsheng1,2 ; Lu, Hanqing1,2
发表期刊	PATTERN RECOGNITION
	2013-10-01
卷号	46 期号:10 页码:2711-2723
文章类型	Article
摘要	Automatically learning and grouping key motion patterns in a traffic scene captured by a static camera is a fundamental and challenging task for intelligent video surveillance. To learn motion patterns, trajectory obtained by object tracking is parameterized, and scene image is spatially and evenly divided into multiple regular cell blocks which potentially contain several primary motion patterns. Then, for each block, Gaussian Mixture Model (GMM) is adopted to learn its motion patterns based on the parameters of trajectories. Grouping motion pattern can be done by clustering blocks indirectly, and each cluster of blocks corresponds to a certain motion pattern. For one particular block, each of its motion pattern (Gaussian component) can be viewed as an instance, and all motion patterns (Gaussian components) constitute a bag which can correspond to multiple semantic clusters. Therefore, blocks can be grouped as a Multi-instance Multi-cluster Learning (MIMCL) problem, and a novel Maximum Margin Multi-instance Multi-cluster Learning ((ML)-L-4) algorithm is proposed. To avoid processing a difficult optimization problem, (ML)-L-4 is further relaxed and solved by making use of a combination of the Cutting Plane method and Constrained Concave-Convex Procedure (CCCP). Extensive experiments are conducted on multiple real world video sequences containing various patterns and the results validate the effectiveness of our proposed approach. (C) 2013 Elsevier Ltd. All rights reserved.
关键词	Scene Understanding Maximum Margin Clustering Multiple Instance Learning (Mil) Gaussian Mixture Model (Gmm) Constrained Concave-convex Procedure (Cccp)
WOS标题词	Science & Technology ; Technology
关键词[WOS]	CLASSIFICATION ; CATEGORIZATION ; SEGMENTATION ; PATTERNS ; SYSTEM ; VIDEO
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000320477400009
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/2877
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.China Singapore Inst Digital Media, Singapore 119615, Singapore
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zhang, Tianzhu,Liu, Si,Xu, Changsheng,et al. M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling[J]. PATTERN RECOGNITION,2013,46(10):2711-2723.
APA	Zhang, Tianzhu,Liu, Si,Xu, Changsheng,&Lu, Hanqing.(2013).M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling.PATTERN RECOGNITION,46(10),2711-2723.
MLA	Zhang, Tianzhu,et al."M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling".PATTERN RECOGNITION 46.10(2013):2711-2723.