CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking
This addresses the challenge of robust long-term visual tracking for applications like surveillance or robotics, but it is incremental as it builds on existing ensemble methods.
The paper tackles the problem of combining complementary visual trackers for long-term tracking, which had been largely ignored in prior work, and shows that their framework CoCoLoT achieves competitive performance on popular benchmarks.
How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking scenarios. Instead, long-term tracking settings have been substantially ignored by the solutions. In this paper, we explicitly consider long-term tracking scenarios and provide a framework, named CoCoLoT, that combines the characteristics of complementary visual trackers to achieve enhanced long-term tracking performance. CoCoLoT perceives whether the trackers are following the target object through an online learned deep verification model, and accordingly activates a decision policy which selects the best performing tracker as well as it corrects the performance of the failing one. The proposed methodology is evaluated extensively and the comparison with several other solutions reveals that it competes favourably with the state-of-the-art on the most popular long-term visual tracking benchmarks.