摘要
Crowded scene analysis is currently a hot and challenging topic in computer vision field. The ability to analyze motion patterns from videos is a difficult, but critical part of this problem. In this paper, we propose a novel approach for the analysis of motion patterns by clustering the tracklets using an unsupervised hierarchical clustering algorithm, where the similarity between tracklets is measured by the Longest Common Subsequences. The tracklets are obtained by tracking dense points under three effective rules, therefore enabling it to capture the motion patterns in crowded scenes. The analysis of motion patterns is implemented in a completely unsupervised way, and the tracklets are clustered automatically through hierarchical clustering algorithm based on a graphic model. To validate the performance of our approach, we conducted experimental evaluations on two datasets. The results reveal the precise distributions of motion patterns in current crowded videos and demonstrate the effectiveness of our approach.
Crowded scene analysis is currently a hot and challenging topic in computer vision field. The ability to analyze motion patterns from videos is a difficult, but critical part of this problem. In this paper, we propose a novel approach for the analysis of motion patterns by clustering the tracklets using an unsuper vised hierarchical clustering algorithm, where the similarity between tracklets is measured by the Longest Common Subsequences. The tracklets are obtained by tracking dense points under three effective rules, therefore enabling it to capture the motion patterns in crowded scenes. The analysis of motion patterns is im plemented in a completely unsupervised way, and the tracklets are clustered automatically through hierarchical clustering algorithm based on a graphic model. To validate the per formance of our approach, we conducted ex perimental evaluations on two datasets. The results reveal the precise distributions of mo tion patterns in current crowded videos and demonstrate the effectiveness of our approach.
基金
supported in part by National Basic Research Program of China (973 Program) under Grant No. 2011CB302203
the National Natural Science Foundation of China under Grant No. 61273285
