Adaptive velocity particle filtering for tracking of targets in noisy environment

Particle Filter (PF) is considered as an extension of the Kalman filter to deal with non-Gaussian non-linear dynamic systems. The key idea is to construct a posterior probability by a set of hypotheses representing a potential state of the system. Sample impoverishment is the flaw of the PF techniques in the case of noisy observations. Recently, evolutionary algorithms are added to PF based methods to improve their functionality in noisy environments. A new PF based method called Adaptive Velocity Particle Filter (AVPF) is introduced to overcome this flaw of the PF. The experimental results show that the proposed method has a superior performance in relation to other evolutionary PF in cases of noisy observations.