Uav identification based on improved YOLOv7 under foggy condition

One-stage algorithm can be effectively used in normal conditions, showing excellent performance on unmanned aerial vehicle (UAV) detection. However, when facing inclement weathers, such as foggy environment, it cannot give a satisfactory outcome we crave for. At the same time, UAV, a tiny object, only contains a few pixels in images and is hided in the fog, causing object obscurity. Concerned about these premises, an improved YOLOv7 is proposed to focus on UAV detection in foggy situation. We adopt BiFormer, a novel dynamic sparse attention through bi-level routing to achieve a flexible distribution of calculation with content awareness, and CL, combined loss function for replacing original IoU metric, to overcome these challenges. At last, Content-Aware ReAssembly of Features (CARAFE) is integrated to the network, aggregating contextual information within a large receptive field. According to this task, we built a new dataset for fog detection (UAV-FG) in which objects are covered by fog, and amount of experiments on UAV-FG datasets verify the effectiveness of our design. Compared with YOLOv7, our method shows consistent and substantial gains (23.21%, 14.35% improvement in mAP@0.5 and mAP@0.5:0.95, respectively) with negligible computational overhead and also satisfies the requirement of real-time detection.