BFO vs. BSO for video object tracking using particle filter (PF)

Abstract

In this paper, we introduced a new algorithm for Video tracking, which is the process of locating a moving object (or multiple objects) over time using a camera. A new particle filter based on bacteria foraging optimization (PF-BFO) is introduced in field of video object tracking. This paper reviews particle filter and using it for tracking. Particle Swarm Optimization (PSO) is also described. Moreover, using the combination of PSO with PF (PF-PSO) in video object tracking is reviewed. Bacterial Foraging Optimization (BFO) is a novel heuristic algorithm inspired from forging behavior of E. coli. After analysis of optimization mechanism, a series of measures are taken to improve the classic BFO by using Particle filter. The PSO is a meta-heuristic which is also inspired from insects' life as ACO. Even both methods use a population of entities. The comparison between PF-BFO and PF-PSO for video object tracking is presented in this work. The results show that PF is strong tool in tracking field. On the other hand, PF-BFO method presents outstanding performance versus PF-PSO.