Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking
This addresses appearance learning challenges in multi-target tracking for applications like surveillance, though it appears incremental as it builds on existing KSVD and tracking frameworks.
The paper tackles the problem of learning target appearance in online multi-target tracking by developing a spatial discriminative KSVD dictionary algorithm (STKSVD) that incorporates spatial and temporal information to handle variations like posture changes and occlusions. The method outperforms existing approaches on the 2DMOT2015 dataset using ACF human detection.
In this paper, we present a new spatial discriminative KSVD dictionary algorithm (STKSVD) for learning target appearance in online multi-target tracking. 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 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 sparse code, linear classifier parameters and minimize reconstruction error in a single optimization system. Our appearance learning algorithm and tracking framework employ 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.