Learning Random Noise Salient Feature Fusion Siamese Network for Low-Resolution Object Tracking (Student Abstract)

Authors

  • Md Maklachur Rahman Texas A&M University, College Station, TX, USA
  • Tracy Hammond Texas A&M University, College Station, TX, USA

DOI:

https://doi.org/10.1609/aaai.v38i21.30500

Keywords:

Computer Vision, Visual Object Tracking, Object Tracking, Single Object Tracking, Low-resolution Tracking, Deep Learning

Abstract

Despite Siamese trackers’ substantial potential, they offer sub-optimal tracking performance in low-resolution (LR) contexts. We introduce a Random Noise Salient Feature Fusion Learning Network to address this issue. This method integrates random noise-infused feature maps into a similaritylearning matching model. This integration acts as an effective regularization technique, enhancing the network’s generalization capabilities in LR environments. Additionally, by integrating attention mechanisms, we enhance the discriminative ability of the network, assigning more weights to important features. This directs the network’s focus toward the most salient regions of the feature map, ensuring improved accuracy without a significant increase in parameter overhead, and maintaining a high operating speed. To validate the effectiveness of our method, we performed qualitative and quantitative comparisons with state-of-the-art (SOTA) trackers.

Published

2024-03-24

How to Cite

Rahman, M. M., & Hammond, T. (2024). Learning Random Noise Salient Feature Fusion Siamese Network for Low-Resolution Object Tracking (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23626-23627. https://doi.org/10.1609/aaai.v38i21.30500