Enforcing Template Representability and Temporal Consistency for Adaptive Sparse Tracking
This work addresses the challenge of drifting in visual tracking for applications like surveillance or robotics, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of visual tracking under appearance variations by proposing a novel sparse tracking algorithm that enforces template representability and temporal consistency (TRAC), resulting in significant outperformance over state-of-the-art trackers on 12 benchmark sequences.
Sparse representation has been widely studied in visual tracking, which has shown promising tracking performance. Despite a lot of progress, the visual tracking problem is still a challenging task due to appearance variations over time. In this paper, we propose a novel sparse tracking algorithm that well addresses temporal appearance changes, by enforcing template representability and temporal consistency (TRAC). By modeling temporal consistency, our algorithm addresses the issue of drifting away from a tracking target. By exploring the templates' long-term-short-term representability, the proposed method adaptively updates the dictionary using the most descriptive templates, which significantly improves the robustness to target appearance changes. We compare our TRAC algorithm against the state-of-the-art approaches on 12 challenging benchmark image sequences. Both qualitative and quantitative results demonstrate that our algorithm significantly outperforms previous state-of-the-art trackers.