Instance Significance Guided Multiple Instance Boosting for Robust Visual Tracking
This work addresses visual tracking robustness for applications like surveillance and robotics, representing an incremental improvement over prior MILBoost methods.
The paper tackles the drifting problem in visual tracking by extending an online MILBoost approach to incorporate instance significance estimation, resulting in a method that outperforms existing MIL-based and boosting-based trackers on challenging public datasets.
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that sequentially chooses weak classifiers by maximizing the bag likelihood. In this paper, we extend this idea towards incorporating the instance significance estimation into the online MILBoost framework. First, instead of treating all instances equally, with each instance we associate a significance-coefficient that represents its contribution to the bag likelihood. The coefficients are estimated by a simple Bayesian formula that jointly considers the predictions from several standard MILBoost classifiers. Next, we follow the online boosting framework, and propose a new criterion for the selection of weak classifiers. Experiments with challenging public datasets show that the proposed method outperforms both existing MIL based and boosting based trackers.