Multi-Branch Siamese Networks with Online Selection for Object Tracking
This work addresses object tracking for computer vision applications, presenting an incremental improvement over existing Siamese network methods.
The paper tackled the problem of object tracking by proposing a multi-branch Siamese network with an online selection mechanism to choose the most efficient CNN branch for target representation, achieving improved performance and real-time tracking compared to standard Siamese trackers on benchmarks.
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.