Logo image
Vision-Radar Fusion-Based Dynamic Sparse Intrusion UAV Detection for Low-Air Security
Conference proceeding

Vision-Radar Fusion-Based Dynamic Sparse Intrusion UAV Detection for Low-Air Security

Yiyao Wan, Jiahuan Ji, Fuhui Zhou, Qihui Wu, Tony Q. S. Quek and IEEE
2024 16th International Conference on Wireless Communications and Signal Processing (WCSP), pp.560-565
24/10/2024

Abstract

Autonomous aerial vehicles deep learning Detectors dynamic sparse end-to-end Hands Radar Security Semantics Signal processing Transforms UAV detection Vehicle dynamics vision-radar fusion Wireless communication
Precise intrusion unmanned aerial vehicle (UAV) detection over long distances is of crucial importance for guaranteeing the low-air security. Although many deep learning-based vision detectors have been developed, they still rely on a large amount of hand-crafted fixed feature priors. Thus, the existing static dense-based detectors suffer from the severe mismatch and imbalance between the small size and high mobility of UAVs. To solve the problem, a novel vision-radar fusion-based dynamic sparse network (Vira-DSNet) is proposed for more balanced and precise UAV detection. The Vira-DSNet exploits our designed dynamic sparse candidate generator and radar-guided semantic feature transform module to generate a small set of customized high-quality object candidates and UAV semantic features based on the radar data. Furthermore, based on Hungarian bisection matching, the proposed Vira-DSNet eliminates the post-processing and is completely end-to-end differentiable. Moreover, the Vira-DSNet is deployed in our developed actual vision-radar fusion-based early intrusion UAV detection system to evaluate the performance in practical applications. Experimental results demonstrate that our Vira-DSNet achieves an average precision AP 50 of 88.2%. It is also shown that the average recall AR 1 of Vira-DSNet is higher than the state-of-the-art scheme by 10.1 %.

Metrics

1 Record Views

Details

Logo image