Robust Object Tracking with Discrete Graph-Based Multiple Experts
- Publication Type:
- Journal Article
- IEEE Transactions on Image Processing, 2017, 26 (6), pp. 2736 - 2750
- Issue Date:
|‘The+program+was+the+solution+to+the+problem’+Process+evaluation+of+a+multi-site+driver+licensing+program+in+remote+communities (1).pdf||Published Version||466.71 kB|
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 1992-2012 IEEE. Variations of target appearances due to illumination changes, heavy occlusions, and target deformations are the major factors for tracking drift. In this paper, we show that the tracking drift can be effectively corrected by exploiting the relationship between the current tracker and its historical tracker snapshots. Here, a multi-expert framework is established by the current tracker and its historical trained tracker snapshots. The proposed scheme is formulated into a unified discrete graph optimization framework, whose nodes are modeled by the hypotheses of the multiple experts. Furthermore, an exact solution of the discrete graph exists giving the object state estimation at each time step. With the unary and binary compatibility graph scores defined properly, the proposed framework corrects the tracker drift via selecting the best expert hypothesis, which implicitly analyzes the recent performance of the multi-expert by only evaluating graph scores at the current frame. Three base trackers are integrated into the proposed framework to validate its effectiveness. We first integrate the online SVM on a budget algorithm into the framework with significant improvement. Then, the regression correlation filters with hand-crafted features and deep convolutional neural network features are introduced, respectively, to further boost the tracking performance. The proposed three trackers are extensively evaluated on three data sets: TB-50, TB-100, and VOT2015. The experimental results demonstrate the excellent performance of the proposed approaches against the state-of-the-art methods.
Please use this identifier to cite or link to this item: