Fully Spiking Neural Networks with Target Awareness for Energy-Efficient UAV Tracking

TL;DR

This paper introduces STATrack, a fully spiking neural network framework for UAV visual tracking using only RGB inputs, achieving competitive performance with low energy consumption.

Contribution

It is the first to explore spiking neural networks for UAV visual tracking and proposes a mutual information maximization method to enhance target features.

Findings

Statrack achieves competitive tracking accuracy on UAV benchmarks.

Statrack maintains low energy consumption compared to traditional methods.

The mutual information approach improves target feature representation.

Abstract

Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-efficient visual tracking on unmanned aerial vehicles (UAVs). However, existing efficient SNN-based trackers heavily rely on costly event cameras, limiting their deployment on UAVs. To address this limitation, we propose STATrack, an efficient fully spiking neural network framework for UAV visual tracking using RGB inputs only. To the best of our knowledge, this work is the first to investigate spiking neural networks for UAV visual tracking tasks. To mitigate the weakening of target features by background tokens, we propose adaptively maximizing the mutual information between templates and features. Extensive experiments on four widely used UAV tracking benchmarks demonstrate that STATrack achieves competitive tracking performance while maintaining low energy consumption.