Gestalt laws based tracklets analysis for human crowd understanding

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.