• Proposes a novel active low-altitude target detection method based on the cat's eye effect, integrating MEMS mirrors and APD for high-sensitivity echo reception.
• Combines local pyramid attention (LPA) and field pyramid network (FPN) with SKNet21 to suppress false alarms and enhance small-target identification.
• Achieves mean average precision of 0.809 at IoU 0.50 and 0.324 at IoU 0.50–0.95, with a throughput of 49.8 GFLOPs, demonstrating feasibility and efficiency.
• Addresses critical limitations in current LSS UAV detection, including false alarm reduction and improved detection accuracy in complex environments.