YOLO-Air: An Efficient Deep Learning Network for Small Object Detection in Drone-Based Imagery

Abstract

UAV imagery is widely used in areas like traffic safety, disaster rescue, and airspace management, due to its small size and low cost. However, it poses unique challenges for object detection due to small objects, complex backgrounds, and noise interference. To tackle these challenges, we propose YOLO-Air, a novel small object detection network designed specifically for UAV imagery. We propose SECAConv (Squeeze-Excitation Convolution with Attention), which enhances the feature representation of small objects through dynamic weight allocation and channel attention mechanisms. Additionally, we design the novel AeroFPN (Aerial Feature Pyramid Network) to optimize feature transmission by alleviating shallow feature loss through the inclusion of the xsmall detection head. Furthermore, we develop ASFM (Adaptive Scale Fusion Module), which suppresses background noise interference through effective multi-scale feature fusion and adaptive channel attention mechanisms, thereby improving the network’s ability to detect small objects. Experimental results demonstrate that YOLO-Air achieves significant accuracy improvements on both the VisDrone-DET2019 and AI-TOD datasets. Compared to the baseline YOLOv8n, YOLO-Air improved $mAP_{50}$ from 41.2% to 44.5% on the VisDrone-DET2019 dataset, and from 44.9% to 47.5% on the AI-TOD dataset, while maintaining computational efficiency. These results validate YOLO-Air as an effective solution for small object detection in UAV aerial imagery.