Unmanned aerial vehicles object detection based on image haze removal under sea fog conditions

Unmanned aerial vehicles (UAVs) have gradually become a major air threat to ships because of small size, good maneuverability, and low cost. Vision-based UAV detection offers one the main ways identify protect against UAVs. Unlike land environment, weather is complicated at sea. The visibility an object undermined by such factors as sea fog sunlight, which makes it difficult detect UAVs through vision-based detection. For purpose sea, this paper proposes method based on image haze removal. In proposed method, improved dark channel removal (DCHR) algorithm utilized remove for restore video images. Additionally, co-ordinate attention (CoordAttention, CA) introduced lightweight algorithms You Only Look Once (YOLO) in restored images, so improve precision speed reduce miss rate. Some images are also taken experiments verify feasibility effectiveness method.