Discriminative Siamese Tracker Based on Multi-Channel-Aware and Adaptive Hierarchical Deep Features

Abstract

Most existing Siamese trackers mainly use a pre-trained convolutional neural network to extract target features. However, due to the weak discrimination of the target and background information of pre-trained depth features, the performance of the Siamese tracker can be significantly degraded when facing similar targets or changes in target appearance. This paper proposes a multi-channel-aware and adaptive hierarchical deep features module to enhance the discriminative ability of the tracker. Firstly, through the multi-channel-aware deep features module, the importance values of feature channels are obtained from both the target details and overall information, to identify more important feature channels. Secondly, by introducing the adaptive hierarchical deep features module, the importance of each feature layer can be determined according to the response value of each frame, so that the hierarchical features can be integrated to represent the target, which can better adapt to changes in the appearance of the target. Finally, the proposed two modules are integrated into the Siamese framework for target tracking. The Siamese network used in this paper is a two-input branch symmetric neural network with two input branches, and they share the same weights, which are widely used in the field of target tracking. Experiments on some Benchmarks show that the proposed Siamese tracker has several points of improvement compared to the baseline tracker.

Siamese Trackers Based on Deep Features for Visual Tracking

“…individually output from the convolution layer in the network was proposed to guarantee the tracking accuracy and robustness of VOT [32].…”

“…Studies on the use of neural networks that learn a target-specific saliency map for tracking have also been conducted [30,31]. A tracking algorithm that adopted hierarchical features that were individually output from the convolution layer in the network was proposed to guarantee the tracking accuracy and robustness of VOT [32].…”