Lightweight YOLO-based foreign object detection for mine conveyor belts

The smooth and safe operation of underground conveyor belts is a fundamental prerequisite for efficient and secure coal-mine production. Manual inspection is inefficient and prone to missed detections; therefore, foreign objects upon entering the conveyor belt must be identified accurately and promptly. Due to the dim underground environment, dust interference, and low image contrast, conventional visual processing methods cannot satisfy the requirements of this application scenario. To address these problems, this study develops a lightweight YOLOv8-based detection framework in which Contrast Limited Adaptive Histogram Equalization (CLAHE) is first used as an image-preprocessing strategy to enhance local contrast and suppress noise. The network is then optimized by replacing selected standard convolutions with Alterable Kernel Convolution (AKConv), which was selected because its adaptive sampling offsets and linear parameter scaling are better suited to elongated and irregular mining debris than fixed square kernels or heavier deformable-convolution variants. Compared with the baseline YOLOv8, the proposed model increases Precision from 86.3% to 88.5%, Recall from 82.4% to 85.2%, and mAP@0.5 from 86.5% to 88.9%, while reducing parameters from 11.2 M to 9.5 M and FLOPs from 28.4 G to 23.6 G. These results indicate that the proposed framework improves detection accuracy and inference efficiency, providing a practical technical basis for automated foreign-object monitoring in underground mining safety systems.