Robust object tracking with crow search optimized multi-cue particle filter

Abstract

Particle filter is used extensively for estimation of target nonlinear and non-Gaussian state. However, its performance suffers due to its inherent problem of sample degeneracy and impoverishment. In order to address this, we propose a novel resampling method based upon crow search optimization to overcome low performing particles detected as the outlier. Proposed outlier detection mechanism with transductive reliability achieves faster convergence of the proposed PF tracking framework. In addition, we present an adaptive fusion model to integrate multi-cue extracted for each evaluated particle. Automatic boosting and suppression of particles using the proposed fusion model not only enhance the performance of the resampling method but also achieve optimal state estimation. Performance of the proposed tracker has been evaluated over benchmark video sequences and compared with state-of-the-art solutions. Qualitative and quantitative results reveal that the proposed tracker not only outperforms existing solutions but also efficiently handles various tracking challenges. On average of the outcome, we achieve CLE of 10.99 and F measure of 0.683.