Analyzing Motion Patterns in Crowded Scenes via Automatic Tracklets Clustering

• Published in: China communications 2013-04, Vol.10 (4), p.144-154
• Main Authors: Chongjing, Wang, Xu, Zhao, Yi, Zou, Yuncai, Liu
• Format: Article
• Language: English
• Subjects: automatic clustering; Clustering algorithms; Computer vision; crowded scene analysis; Image motion analysis; motion pattern; Optical filters; Optical imaging; Tracking; tracklet; Videos; 场景分析; 层次聚类算法; 序列测定; 拥挤; 组成部分; 聚类分析; 计算机视觉; 运动模式
• ISSN: 1673-5447
• DOI: 10.1109/CC.2013.6506940

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.