This paper presents a novel method for global anomaly detection in crowded scenes. The proposed method introduces the Particle Swarm Optimization (PSO) method as a robust algorithm for optimizing the interaction force computed using the Social Force Model (SFM). The main objective of the proposed method is to drift the population of particles towards the areas of the main image motion. Such displacement is driven by the PSO fitness function aimed at minimizing the interaction force, so as to model the most diffused and typical crowd behavior Experiments are extensively conducted on public available datasets, namely, UMN and PETS 2009, and also on a challenging dataset of videos taken from Internet. The experimental results revealed that the proposed scheme outperforms all the available state-of-the-art algorithms for global anomaly detection.
Optimizing Interaction Force for Global Anomaly Detection in Crowded Scenes
CRISTANI, Marco;MURINO, Vittorio
2011-01-01
Abstract
This paper presents a novel method for global anomaly detection in crowded scenes. The proposed method introduces the Particle Swarm Optimization (PSO) method as a robust algorithm for optimizing the interaction force computed using the Social Force Model (SFM). The main objective of the proposed method is to drift the population of particles towards the areas of the main image motion. Such displacement is driven by the PSO fitness function aimed at minimizing the interaction force, so as to model the most diffused and typical crowd behavior Experiments are extensively conducted on public available datasets, namely, UMN and PETS 2009, and also on a challenging dataset of videos taken from Internet. The experimental results revealed that the proposed scheme outperforms all the available state-of-the-art algorithms for global anomaly detection.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
