Pedestrian tracking in low contrast regions using aggregated background model and Silhouette Components

We propose an approach for pedestrian detection and tracking in low contrast regions. The approach is composed of two modules. Module-1 improves the pixel-based Mixture of Gaussians (MOG) by aggregated background modeling and varying interval differences. Module-2 exploits the Local Patch Variance (LPV) and Partial Silhouette Template (PST) for compensating the incomplete foregrounds often observed in low contrast scenes regardless of the approaches. Experiments show that the proposed approach performs satisfactorily.