Abstract
To address challenges of background interference and limited multi-scale feature extraction in infrared small target detection, this paper proposes a YOLO-HVS detection algorithm inspired by the human visual system. Based on YOLOv8, we design a multi-scale spatially enhanced attention module (MultiSEAM) using multi-branch depth-separable convolution to suppress background noise and enhance occluded targets, integrating local details and global context. Meanwhile, the C2f_DWR (dilation-wise residual) module with regional-semantic dual residual structure is designed to significantly improve the efficiency of capturing multi-scale contextual information by expanding convolution and two-step feature extraction mechanism. We construct the DroneRoadVehicles dataset containing 1028 infrared images captured at 70-300 m, covering complex occlusion and multi-scale targets. Experiments show that YOLO-HVS achieves mAP50 of 83.4% and 97.8% on the public dataset DroneVehicle and the self-built dataset, respectively, which is an improvement of 1.1% and 0.7% over the baseline YOLOv8, and the number of model parameters only increases by 2.3 M, and the increase of GFLOPs is controlled at 0.1 G. The experimental results demonstrate that the proposed approach exhibits enhanced robustness in detecting targets under severe occlusion and low SNR conditions, while enabling efficient real-time infrared small target detection.