Robust tracking with weighted online structured learning
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Sparse coding based visual tracking: Review and experimental comparison
Pattern Recognition
Robust visual tracking using dynamic classifier selection with sparse representation of label noise
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
A survey of appearance models in visual object tracking
ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
| Hi-index | 0.00 |
Most sparse linear representation-based trackers need to solve a computationally expensive ii-regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient closed-form solution without sacrificing accuracy. Moreover, in order to capture the correlation information between different feature dimensions, we learn a Mahalanobis distance metric in an online fashion and incorporate the learned metric into the optimization problem for obtaining the linear representation. We show that online metric learning using proximity comparison significantly improves the robustness of the tracking, especially on those sequences exhibiting drastic appearance changes. Furthermore, in order to prevent the unbounded growth in the number of training samples for the metric learning, we design a time-weighted reservoir sampling method to maintain and update limited-sized foreground and background sample buffers for balancing sample diversity and adaptability. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.