Multi-Branch Siamese Networks with Online Selection for Object Tracking

TL;DR

This paper introduces a real-time object tracking method that dynamically selects the most suitable CNN branch from multiple pre-trained branches, improving tracking accuracy and efficiency over standard Siamese trackers.

Contribution

It presents a novel multi-branch Siamese network with an online branch selection mechanism for enhanced object tracking performance.

Findings

Achieves real-time tracking with improved accuracy.

Outperforms standard Siamese network trackers on benchmarks.

Utilizes multiple pre-trained CNN branches for diverse target representations.

Abstract

In this paper, we propose a robust object tracking algorithm based on a branch selection mechanism to choose the most efficient object representations from multi-branch siamese networks. While most deep learning trackers use a single CNN for target representation, the proposed Multi-Branch Siamese Tracker (MBST) employs multiple branches of CNNs pre-trained for different tasks, and used for various target representations in our tracking method. With our branch selection mechanism, the appropriate CNN branch is selected depending on the target characteristics in an online manner. By using the most adequate target representation with respect to the tracked object, our method achieves real-time tracking, while obtaining improved performance compared to standard Siamese network trackers on object tracking benchmarks.