Correlation-guided multi-object tracking with correlation feature transfer

Here, the authors propose a correlation-guided Monte Carlo Markov chain (MCMC) solver to promote the efficiency for tracking multiple objects under recursive Bayesian filtering framework. Instead of randomly proposing the target location according to certain distribution, the authors' method guides the MCMC solver to sample among locations that the targets are more likely to appear. The high possible locations for each target are obtained using its corresponding response map by evaluating the correlation between the target appearance and its online model. Furthermore, the proposed tracking framework is natural to transfer the rich domain-specific offline correlation features into the target online model. With the calculation in the Fourier domain and the reversible jump strategy for MCMC, the correlation-guided method is able to track variable multiple objects with high efficiency. At the same time, the correlation feature transfer strategy is capable of improving tracking precision with easy offline training. The proposed method is evaluated by both the synthetic and real scenario videos. The experimental results demonstrate the effectiveness of the proposed method and its superior performance against its counterparts.