To address the challenges of limited detection accuracy and the difficulty of deployment on edge devices caused by dust obstruction, low illumination, and complex background interference in coal mine conveyor belt foreign object detection, this paper proposes an improved algorithm model, RTA-YOLOv11, based on the YOLOv11 framework. First, a Receptive Field Enhancement Module (RFEM) is utilized to expand the field of view by fusing multi-scale perception paths, strengthening the network’s semantic capture capability for subtle targets. Second, a Triplet Attention mechanism is introduced to suppress environmental noise and enhance the saliency of low-contrast foreign objects through cross-dimensional joint modeling of spatial and channel information. Finally, a lightweight detection head based on MBConv is designed, utilizing inverted bottleneck structures and re-parameterization strategies to compress redundant parameters and improve deployment efficiency on edge devices. Experimental results indicate that the mAP@0.5 of the improved RTA-YOLOv11 model is 4.0 percentage points higher than that of the original YOLOv11, with an inference speed of 79 FPS and a reduction in parameters of approximately 22%. Compared with algorithms such as Faster R-CNN, SSD, and YOLOv8, this model demonstrates a superior balance between accuracy and speed, providing an efficient and practical solution for intelligent mine visual perception systems.
Wang et al. (2026) studied this question.