A particle swarm optimisation algorithm with interactive swarms for tracking multiple targets

Monekosso, Dorothy N.; Thida, Myo; Eng, How Lung; Monekosso, Dorothy; Remagnino, Paolo

Abstract

We propose a novel particle swarm optimisation algorithm that uses a set of interactive swarms to track multiple pedestrians in a crowd. The proposed method improves the standard particle swarm optimisation algorithm with a dynamic social interaction model that enhances the interaction among swarms. In addition, we integrate constraints provided by temporal continuity and strength of person detections in the framework. This allows particle swarm optimisation to be able to track multiple moving targets in a complex scene. Experimental results demonstrate that the proposed method robustly tracks multiple targets despite the complex interactions among targets that lead to several occlusions. © 2012 Elsevier B.V. All rights reserved.

• Journal Article Type: Article
• Publication Date: Jan 1, 2013
• Journal: Applied Soft Computing Journal
• Print ISSN: 1568-4946
• Publisher: Elsevier
• Peer Reviewed: Not Peer Reviewed
• Volume: 13
• Issue: 6
• Pages: 3106-3117
• DOI: https://doi.org/10.1016/j.asoc.2012.05.019
• Keywords: interactive swarms, particle swarm optimisation, multi-target tracking, social behaviour, crowded scenes
• Public URL: https://uwe-repository.worktribe.com/output/930930
• Publisher URL: http://dx.doi.org/10.1016/j.asoc.2012.05.019