LDHD-Net: A Lightweight Network With Double Branch Head for Feature Enhancement of UAV Targets in Complex Scenes

Abstract

The development of small UAV technology has led to the emergence of new challenges in UAV countermeasures. The timely detection of UAVs can effectively prevent potential infringements on airspace and privacy. Currently, methods based on deep learning demonstrate excellent performance in target detection. However, in complex scenes, there is a tendency for false alarms (FAs) and misdetections to occur at a higher rate. To solve these problems, we propose a lightweight infrared small target detection algorithm LDHD-Net. First, we design a novel Ghost-Shuffle module in the backbone network to enhance the network feature extraction capability. Meanwhile, we remove redundant layers from the network to make the backbone network more lightweight. Second, we design a hierarchical attention enhancement module in the neck network to improve the saliency of UAV targets and reduce background noise interference. In addition, we design a novel small target detection structure and prediction heads in the shallow layers of the network to improve small target detection accuracy. Finally, we design a novel attention dual-branch head to reduce interference between different tasks and improve the real-time performance of algorithm detection. The experimental results show that compared with the original model, inference time remains essentially the same, LDHD-Net parameters are only 3.9 M and AP improves by 12.6%. Compared to SOTA methods, LDHD-Net shows better performance on SIDD and Anti-UAV410 datasets. The algorithm effectively improves the accuracy and real-time detection of UAVs in complex scenes.