Collaborative model based UAV tracking via local kernel feature

• Published in: Applied soft computing Vol. 72; pp. 90 - 107
• Main Authors: Wang, Yong, Luo, Xinbin, Ding, Lu, Fu, Shan, Hu, Shiqiang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2018
• Subjects: Collaborative model; Local kernel feature; Structure support vector machine; UAV tracking; Local kernel feature; UAV tracking; Structure support vector machine; Collaborative model
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2018.07.049

•A collaborative model is developed to take advantages of both holistic model and part model.•A local kernel feature is designed to encode the geometric information of a target.•A metric based on the local feature is proposed to measure the reliability of a tracking object. The estimation results can be treated to fusion weights to locate the final target position.•Extensive experiments are carried out to demonstrate the effectiveness and robustness of our method with comparisons to state-of-the-art methods. Partial occlusion is one of a challenging problem in unmanned aerial vehicle (UAV) tracking. In this paper, we propose a novel collaborative model based tracking method which attempts to exploit a holistic model and a part model that tracks an object consistently through the entire video sequence. Specifically, we first develop a robust local kernel feature which learns the data around to encode the geometric information of the object. Next, the target is divided into four parts. And structure support vector machine (SSVM) is employed to integrate with the local feature to a robust visual tracking framework. Furthermore, we adopt a reliable metric to measure the reliability of a patch. Kalman filter is used to fuse the holistic model and part model tracking results smoothly according to the metric. Extensive experimental results demonstrate our tracker achieves comparable performance to state-of-the-art methods.