Foreground-aware Siamese tracker with dynamic template in wireless sensor networks

Abstract

Accuracy and reliability are the main problems to be considered when using wireless sensor networks for target tracking. Deep learning has a good prospect in visual object tracking, in which Siamese based trackers achieve a balance between performance and computational efficiency.Template adaptability and feature expression of the target are crucial for Siamese trackers which aim to locate the target by learning a decision-making based similarity evaluation. However, the fixed template can hardly handle the severe target variation and the background information in the complex scene will also interfere the similarity evaluation learning process.In these work, we propose a foreground-aware Siamese tracker with dynamic template to tackle these issues. Firstly, we construct a local effective template feature attention network to guide the template updating according to context tracking information. Then the similarity attention update mask is generated to enhance the discriminative ability of tracker to adapt to complex tracking task. Further, we propose a foreground-aware channel selection module which let the tracker pay more attention to the foreground semantic feature channel in the target search area, thus our tracker can suppress the tracking drift of Siamese trackers in the background clutter scene. Extensive experiments demonstrate that our tracker can significantly improve the performance of our baseline and performs favorably against many state-of-the-art trackers.