YOLO-SCC: A Lightweight Object Detection Method for Mine Safety

Abstract

Highlights What are the main findings? Improved Precision and Localization Quality: Compared with YOLO26n, YOLO-SCC improves precision by 6.1 percentage points and mAP50-95 by 3.3 percentage points, while recall and mAP50 increase by 0.9 and 0.1 percentage points, respectively. Validation of Module Effectiveness: The designed SCC enhancement structure (SPDConv, CBAM, ContextAggregation) effectively addresses three core challenges in underground detection: detail loss, background interference, and insufficient contextual information. The efficacy of each module is validated through ablation studies. What are the implications of the main findings? Provides a Feasible Solution for Lightweight Detection in Complex Industrial Scenarios: This study demonstrates that through carefully designed lightweight enhancement modules, the robustness of models in extreme environments can be significantly improved without substantially increasing computational costs. This offers important guidance for deploying high-performance safety monitoring systems on resource-constrained edge devices. Directly Advances Intelligent Safety in Coal Mining: By enabling more accurate and reliable detection of underground personnel, this method can help reduce safety incidents caused by missed detections or false alarms. It provides core technological support for developing a new generation of intelligent mine safety monitoring platforms and emergency response systems. Abstract To address the challenges in personnel detection in underground coal mines, such as uneven lighting, dust occlusion, cluttered backgrounds, and significant scale variation of targets, this paper proposes a lightweight object detection method named YOLO-SCC. Based on the lightweight detection network YOLO26n, the SCC lightweight enhancement structure, composed of SPDConv, CBAM, and ContextAggregation, is constructed to improve feature representation and target recognition capability in complex underground environments while striving to maintain model compactness. Specifically, SPDConv optimizes the downsampling process to reduce the loss of feature details, which helps preserve edge and texture information of miners under low-light conditions, at long distances, or at small scales. CBAM adaptively weights features from both channel and spatial dimensions, enhancing the model’s focus on the main body of miners and suppressing irrelevant interference from light reflections, equipment structures, and dust noise. The ContextAggregation module aggregates richer contextual semantic information, strengthening the model’s discriminative ability for personnel targets under occlusion, dense distribution, and complex backgrounds. Experimental results show that with only a modest increase in parameters (from 2.38 MB to 2.88 MB) and computational cost (from 5.2 GFLOPs to 6.0 GFLOPs), YOLO-SCC achieves precision of 88.8%, recall of 82.2%, mAP50 of 85.3%, and mAP50-95 of 51.2%. These represent improvements of 6.1, 0.9, 0.1, and 3.3 percentage points, respectively, over the baseline YOLO26n. The results suggest that YOLO-SCC primarily improves false-positive suppression and localization quality in complex underground environments while maintaining a lightweight model scale.