An Efficient Misalignment Method for Visual Tracking Based on Sparse Representation

Abstract

SUMMARYSparse representation has been widely applied to visual tracking for several years. In the sparse representation framework, tracking problem is transferred into solving an L1 minimization issue. However, during the tracking procedure, the appearance of target was affected by external environment. Therefore, we proposed a robust tracking algorithm based on the traditional sparse representation jointly particle filter framework. First, we obtained the observation image set from particle filter. Furthermore, we introduced a 2D transformation on the observation image set, which enables the tracking target candidates set more robust to handle misalignment problem in complex scene. Moreover, we adopt the occlusion detection mechanism before template updating, reducing the drift problem effectively. Experimental evaluations on five public challenging sequences, which exhibit occlusions, illuminating variations, scale changes, motion blur, and our tracker demonstrate accuracy and robustness in comparisons with the state-of-the-arts. key words : visual tracking, sparse representation, 2D transformation, template update

Human Tracking Objects in Dark Situations Based on Thermal Using Support Vector Machines, L1 Tracker Using Accelerated Proximal Gradient Approach, and Kernelized Correlation Filter Methods

“…The main differences between the two methods are different minimization models and a much faster numerical solver for the resulting L1 minimization problem. L1APG is used to minimize the sum, while the APG method is used to solve unrestricted problems related to L1 namely image restoration [14] then reduce computational costs and make the tracking algorithm real time, although tracking in this method shows good performance by using trivial templates, the tracking process can be generalized better [16].…”