YOLO-AFP: A More Robust Network for Aerial Object Detection

In practical applications of aerial object detection, real-time unmanned aerial vehicle (UAV) imagery is often affected by noise, low light, and cloud occlusion, leading to poor image quality. The performance of mainstream UAV object detection algorithms tends to degrade when applied to such imagery, as these models are typically trained and evaluated on clean datasets. To address these challenges, we propose a robust YOLO based network, YOLO-AFP, which integrates an atrous feature pyramid (AFP) module. This allows the model to generalize effectively under various corrupted conditions, despite being trained only on clean data. First, we introduced AFP module, which employs atrous convolutions with varying dilation rates, and integrate it into the path aggregation network (PAN) to expand the receptive field. This enhancement allows the model to better capture object-background relationships and reduce feature corruption caused by local pixel changes. Second, we propose a robust ResNet-SPPF as the backbone network, which retains strong feature extraction capabilities while having fewer residual connections compared to YOLO's Darknet. This design effectively mitigates the impact of corrupted image features on subsequent feature extraction. To validate the effectiveness of our method, we constructed two new datasets based on the DOTAv1.0 dataset, named DOTA-HC and DOTA-HCloud. Experimental results demonstrate that on the DOTA-HC dataset, YOLO-AFP achieved a mPC of 60.8% and a rPC of 80.3%, outperforming the best real-time detection model by 1.5% and 2%, respectively. On the DOTA-HCloud dataset, YOLO-AFP achieved an rPC of 88.5%, surpassing the top model by 1.1%.