Robust Instance Tracking via Uncertainty Flow
This work addresses robustness in instance tracking for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of tracking failure due to distractors and appearance changes by incorporating dense optical flow with flow uncertainty, resulting in new state-of-the-art tracking robustness.
Current state-of-the-art trackers often fail due to distractorsand large object appearance changes. In this work, we explore the use ofdense optical flow to improve tracking robustness. Our main insight is that, because flow estimation can also have errors, we need to incorporate an estimate of flow uncertainty for robust tracking. We present a novel tracking framework which combines appearance and flow uncertainty information to track objects in challenging scenarios. We experimentally verify that our framework improves tracking robustness, leading to new state-of-the-art results. Further, our experimental ablations shows the importance of flow uncertainty for robust tracking.