Tracking-by-detection of multiple persons by a resample-move particle filter

Camera networks make an important component of modern complex perceptual systems with widespread applications spanning surveillance, human/machine interaction and healthcare. Smart cameras that can perform part of the perceptual data processing improve scalability in both processing power and network resources. Based on these insights, this paper presents a particle filter for multiple person tracking designed for an FPGA-based smart camera. We propose a new joint Markov Chain Monte Carlo-based particle filter (MCMC-PF) with short Markov chains, devoted to each individual particle, in order to sample the particle swarm in relevant regions of the high dimensional state-space with increased particle diversity. Finding an efficient sampling method has become another challenge when designing particle filters, especially for those devoted to more than two or three targets. A proposal distribution, combining diffusion dynamics, learned HOG + SVM person detections, and adaptive background mixture models, limits here the well-known burst in terms of particles and MCMC iterations. This informed proposal based on saliency maps has only been marginally used in the literature in a joint state space PF framework. The presented qualitative and quantitative results-for proprietary and public video datasets-clearly show that our tracker outperforms the well-known MCMC-PF in terms of (1) tracking performances, i.e. robustness and precision, and (2) parallelization capabilities as the MCMC-PF processes the particles sequentially.