Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking

In this paper, we present a new spatiotemporal discriminative KSVD dictionary algorithm (STKSVD) for learning target appearance in online multi-target tracking system. Different from other classification/recognition tasks (e.g. face, image recognition), learning target's appearance in online multi-target tracking is impacted by factors such as: posture/articulation changes, partial occlusion by background scene or other targets, background changes (human detection bounding box covers both human parts and part of the scene), etc. However, we observe that these variations occur gradually relative to spatial and temporal dynamics. We characterize the spatial and temporal information between target's samples through a new STKSVD appearance learning algorithm to better discriminate targets. Our STKSVD method is able to learn discriminative sparse code, linear classifier parameters, and minimize reconstruction error in single optimization system. Our appearance learning algorithm and tracking framework employs two different methods of calculating appearance similarity score in each stage of a two-stage association: a linear classifier in the first stage, and minimum residual errors in the second stage. The results tested using 2DMOT2015 dataset and its public Aggregated Channel Features (ACF) human detection for all comparisons show that our method outperforms the existing related learning methods.