Context multi-task visual object tracking via guided filter

• Published in: Signal processing. Image communication 2018-03, Vol.62, p.117-128
• Main Authors: Wang, Yong, Luo, Xinbin, Fu, Shan, Hu, Shiqiang
• Format: Article
• Language: English
• Subjects: Alternating direction method of multipliers; Context information; Filtration; Guided filter; Kalman filters; Learning; Multi-task sparse learning; Optical tracking; Principal components analysis; Tracking control systems; Visual object tracking; Visual tasks
• ISSN: 0923-5965; 1879-2677
• DOI: 10.1016/j.image.2017.12.008

In this paper, we formulate particle filter based tracking as a multi-task sparse learning problem that exploits context information. The target and context information which modeled as linear combinations of principal component analysis (PCA) basis is formed as dictionary templates. The target is treated as the guidance and the sampling examples are filtered depending on the similarity between the target and each input. The edge preserving smoothing property of the guided filter is a key factor for object tracking. First, valuable candidates can be selected and the inaccurate candidates become blurry. Therefore, the guided filter can help to distinguish the target from numerous candidates easily. Second, partial occluded target can be recovered by the filtering process via the guidance image. Thus, the drifting problem can be alleviated. Then multi-task sparse learning is employed to learn the target and context information. The proposed learning problem is efficiently solved using an alternating direction method of multipliers (ADMM) method that yields a sequence of closed form updates. We test our tracker on challenging video sequences that involve drastic illumination changes, large pose variations, and heavy occlusions. Experimental results show that our tracker consistently outperforms state-of-the-art trackers. •A multi-task sparse learning tracker is proposed.•We integrate context information into subspace learning method.•The guided filter is employed to alleviate the effect of illumination and background clutter.•The decomposition model is utilized to separate the common part and outliers in the candidates.