A robust visual tracking method via local feature extraction and saliency detection

Abstract

Visual object tracking is a fundamental problem in computer vision. It heavily relies on feature description for the appearance of object. In this paper, we present a robust algorithm which exploits the locally adaptive regression kernel (LARK) feature for visual tracking. The proposed approach formulates the LARK feature in a tracking by detection framework. In addition, we compute a target-specific saliency map as LARK feature with the guidance of the tracking framework. The tracking problem is solved by maximizing an object location likelihood function. We adopt Fast Fourier Transform for fast learning and detection in this work. Extensive experimental results on challenging videos show that the proposed algorithm performs favorably against state-of-the-art methods in terms of accuracy and robustness.