Robust Visual Tracking Using Multi-Frame Multi-Feature Joint Modeling

Abstract

It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal consistency across consecutive frames and multiple feature cues in a unified model. Motivated by this idea, we propose a novel correlation filter-based tracker in this work, in which the temporal relatedness is reconciled under a multi-task learning framework and the multiple feature cues are modeled using a multi-view learning approach. We demonstrate the resulting regression model can be efficiently learned by exploiting the structure of blockwise diagonal matrix. A fast blockwise diagonal matrix inversion algorithm is developed thereafter for efficient online tracking. Meanwhile, we incorporate an adaptive scale estimation mechanism to strengthen the stability of scale variation tracking. We implement our tracker using two types of features and test it on two benchmark datasets. Experimental results demonstrate the superiority of our proposed approach when compared with other state-of-the-art trackers. MATLAB code is available from our project homepage http://bmal.hust.edu.cn/ project/KMF2JMTtracking.html.

Learning Low-Rank and Sparse Discriminative Correlation Filters for Coarse-to-Fine Visual Object Tracking

“…Some recent studies deal with the temporal correlations via two approaches, i.e., involving more historical samples and exploiting target re-detection. Specifically, by incorporating weighted historical samples into the learning stage, the resulting adaptive decontamination of the training set [51], [52], [53], [54] achieves robust tracking performance. In the same spirit, Efficient Convolution Operators (ECO) [55] significantly improve the computational efficiency by decreasing the number of historical frames via a data clustering technique.…”