Frequency-Enhanced and Multi-Scale Feature Fusion YOLOv11 for Low-Illumination Weak Projectile Target Recognition in...

To solve the problem where the low contrast and extremely small target size in the three-sky-screen target-integrated linear array CCD sensor measurement system under low-illumination conditions make it difficult to accurately identify projectile targets, this paper proposes a method of Frequency-Enhanced and Multi-scale Feature Fusion YOLOv11 (FEMFF-YOLOv11). It introduces a frequency-domain enhancement module in the backbone to improve feature discriminability, and deformable offset convolution is incorporated to handle geometric deformations. It also adds a multi-scale attention aggregation module in the neck to strengthen weak target features and suppress false targets such as near-lens flying objects. The detection head is optimized by replacing the low-resolution P5 layer with a high-resolution P2 layer for better projectile target localization. Experiments are conducted on a self-built linear array CCD projectile dataset. The results demonstrate that compared with YOLOv11 and other mainstream algorithms, our method achieves 87.35% precision and 85.13% recall under 300 lx low-illumination conditions. It also maintains 85.91% precision and 82.56% recall even at 50 lx, significantly outperforming all competitors.