Deep learning-based UAV detection in the low altitude clutter background

TL;DR

This paper presents a deep contrastive learning approach for detecting low-altitude UAVs amidst ground clutter, significantly improving detection accuracy and reliability over existing methods.

Contribution

The paper introduces a novel deep contrastive learning-based method that effectively suppresses ground clutter and enhances UAV detection in low-altitude radar signals.

Findings

Achieves over 5% higher detection accuracy than state-of-the-art methods.

Effectively suppresses ground clutter and reduces false alarms.

Improves detection reliability in low-altitude environments.

Abstract

Unmanned aerial vehicles (UAVs) are widely used due to their low cost and versatility, but they also pose security and privacy threats. Therefore, reliable detection for low-altitude UAVs is an important issue. The strong ground clutter makes the radar echoes from small UAVs submerged in noise, resulting in low radar detection reliability. A low-altitude UAV detection method based on deep contrastive learning is proposed to address the above problems: Concretely, a low-altitude UAV radar echo model under low-altitude clutter interference is first established. Based on the echo components and the UAV Doppler domain identifiable mechanism, a time-frequency transformation method combining ZAM transform and morphological operations is used to suppress the ambiguity problem under clutter. Then feature extraction and fusion method introducing contrast learning is utilized to suppress non-target ground clutter interference. Finally, a detector relying on semantic features is designed for the reliable identification of low-altitude UAVs. The experiments carried out on both real and simulated data confirm that the proposed method can effectively suppress ground clutter and reliably extract recognizable semantic features of UAVs. The proposed method achieves lower false and missing alarms compared with recent state-of-art solutions and improves the detection accuracy by more than 5% for the same signal-to-noise ratio, which effectively improves the detection reliability.