SIRI-YOLO: A Foreign Object Detection Method for Belt Conveyors in High-Entropy Underground Scenes.

To address the poor detection performance in low-light underground coal mine belt conveyors caused by information entropy degradation and high background noise, as well as the difficulty in multi-scale target extraction due to uneven entropy distribution, this paper proposes an efficient foreign object detection model named SIRI-YOLO based on an improved YOLOv11n architecture. First, a Self-Calibrating Illumination Network (SCINet) is introduced to restore image information entropy and enhance low-light adaptability. Second, the C2PSA module is enhanced to C2PSA-IRMB by incorporating an Inverted Residual Mobile Block (IRMB), improving multi-scale feature utilization and reducing ineffective entropy increase. Third, an improved Reparameterized Generalized Feature Pyramid Network (RepGFPN) is adopted to strengthen the fusion of high-level semantics and low-level spatial features, reducing information entropy loss during feature pyramid transfer. Finally, the Inner-MPDIoU loss function is introduced to replace CIoU, achieving more accurate entropy minimization from a KL divergence perspective. Experimental results on a dataset containing large coal chunks and anchor rods show that SIRI-YOLO achieves 92.8% mAP@50, 59.4% mAP@50:95, 89.5% precision, and 87.2% recall, with only 2.92M parameters and 70.01 FPS, outperforming mainstream YOLO models. Furthermore, on the public ExDark low-light dataset, SIRI-YOLO improves mAP@50 by 4.2% over YOLOv11n, demonstrating strong generalization across different low-light and complex scenarios. The proposed method effectively handles uneven illumination, scale variation, and complex backgrounds, offering a practical solution for coal mine safety through system entropy reduction.