A single target tracking algorithm based on Generative Adversarial Networks

TL;DR

This paper introduces a single target tracking algorithm that effectively handles occlusions by predicting target motion during occlusion periods using GAN-based techniques, improving tracking robustness and accuracy.

Contribution

The proposed algorithm integrates occlusion awareness and motion prediction modules to enhance single target tracking performance under occlusion conditions.

Findings

Achieved higher EAO, Accuracy, and Robustness on VOT2018 dataset compared to SiamRPN ++.

Successfully tracked targets in occluded scenarios with improved stability.

Demonstrated effectiveness of occlusion prediction in real-world tracking tasks.

Abstract

In the single target tracking field, occlusion leads to the loss of tracking targets is a ubiquitous and arduous problem. To solve this problem, we propose a single target tracking algorithm with anti-occlusion capability. The main content of our algorithm is to use the Region Proposal Network to obtain the tracked target and potential interferences, and use the occlusion awareness module to judge whether the interfering object occludes the target. If no occlusion occurs, continue tracking. If occlusion occurs, the prediction module is started, and the motion trajectory of the target in subsequent frames is predicted according to the motion trajectory before occlusion. The result obtained by the prediction module is used to replace the target position feature obtained by the original tracking algorithm. So we solve the problem that the occlusion causes the tracking algorithm to lose the target. In actual performance, our algorithm can successfully track the target in the occluded dataset. On the VOT2018 dataset, our algorithm has an EAO of 0.421, an Accuracy of 0.67, and a Robustness of 0.186. Compared with SiamRPN ++, they increased by 1.69%, 11.67% and 9.3%, respectively.