Adaptive Multi-Feature Fusion for Robust Object Tracking

Abstract

In this paper, in order to better describe the object, an adaptive multi-feature fusion method is proposed, which makes full use of the advantages of various features. Firstly, hierarchical convolution features and two hand-crafted features are fused linearly, and the weights of different features are adjusted adaptively to obtain the optimal object representation in the tracking process. Secondly, a translation filter and a scale filter are adopted to estimate the object's exact position and scale, respectively. Finally, in the model update stage, an efficient adaptive model update strategy is used to improve the performance, which can significantly alleviate the model noises. Extensive experimental results on well-known benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art tracking methods.