Gestalt laws based tracklets analysis for human crowd understanding. (March 2018)

• Record Type: Journal Article
• Authors: Zhao, Weiqi; Zhang, Zhang; Huang, Kaiqi
• Is Part Of: Pattern recognition. Volume 75(2018:Mar.)
• Page Start: 112
• Page End: 127
• Publication Date: 2018-03
• Subjects: Similarity measurement -- Group detection -- Semantic regions -- Hierarchical clustering; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.06.020
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A unified similarity measurement for spatiotemporal tracklets is proposed. The short-term group and long-term path can be learnt in a unified framework. A crowd analysis dataset is constructed to promote the study of crowd behavior. Abstract: Crowded scene analysis is a popular research topic due to its great application potentials, such as intelligent video surveillance and crowd density estimation. In this paper, we propose a novel approach to detecting crowd groups and learning semantic regions with a unified hierarchical clustering framework. According to the Gestalt laws of grouping, we propose three priors to define a unified similarity metric to measure the similarities of pairs of original tracklets and pairs of representative tracklets from different crowd groups, so that the short-term crowd groups and the long-term semantic paths commonly composed of several short-term crowd groups can be detected by a bottom-up hierarchical clustering algorithm simultaneously. In order to verify our method at the longer time duration video sequences in the crowded scene, we construct a new crowd database (CASIA crowd database 1 ) with various crowd densities in real scenes. Extensive experiments on our CASIA crowd database, Collective Motion Database and CUHK database are performed, and the results demonstrate that our approach is effective and reliable for crowd detection and semantic scene understanding in various crowd densities, especially for the crowd analysis in long temporal video clips.