Knowledge Commons of Institute of Automation,CAS
M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling | |
Zhang, Tianzhu1,2![]() ![]() ![]() | |
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 | |
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. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论