Channel Positive and Negative Feedback Network for Target Tracking

Abstract

Aiming at alleviate the detrimental effect of similar object interferences and target state changes in SiamRPN tracker, a Channel Positive and Negative Feedback Network (CPFN) is proposed, in which the Gaussian score map is generated by the feature channels selected by a Gaussian kernel, and the map is combined with the classification branches of SiamRPN. In this way, the feature channels are divided into positive feedback channels and interference channels, and these feature channels are effectively utilized. In addition, a channel weight update strategy is proposed to enhance the robustness of the tracker and avoid template pollution caused by inadequate template update. Extensive experiments on tracking benchmarks including VOT2016, VOT2018, VOT2019, OTB100, UAV123, LaSOT and GOT-10k show that the proposed CPFN outperforms the state-of-the-art methods based on small backbone network in terms of accuracy and achieves high-speed tracking. INDEX TERMS Target tracking, siamese network, gaussian kernel, feature combination [13]. With the development of deep learning, deep features have shown excellent effects in image processing and are widely used in image classification, face recognition, object

Feature Complement for Visual Tracking Based on Global Feature Comparison

“…The OTB100 dataset uses precision plot and success plot to evaluate the tracking model. In this paper, we compare the proposed model with several representative trackers, including SiamRPN++ [25], SiamBAN [6], DiMP50 [2], DiMP18 [2], CPFN [5], ATOM [9], SiamRPN [26], TADT [29], Grad-Net [28]. Observing the results in Figure 5, we can see that our proposed FSGFC model ranks first, surpassing most of the contrast trackers.…”