基于改进YOLOv4算法的矿用设备关键部件识别研究

Recognition of key components in mining equipment based on improved YOLOv4 algorithm

为了使煤矿设备检测平台能够精准快速识别出复杂矿用设备的关键部件,提出一种基于YOLOv4的轻量化改进模型GhostNet-YOLOv4,模型引入GhostNet作为YOLOv4的CSPDarkNet53,减少模型参数量与冗余计算量的同时,降低模型训练时间;GhostNet当中的shortcut结构减少网络退化现象,提高模型特征提取能力。实验结果证明,改进模型参数量与YOLOv4相比减少83%,与MobileNet3-YOLOv4相比减少6%,识别平均准确率达到92.67%,图片检测速度(FPS)可达到33.75帧/s,相较于YOLOv4提升了43%。在复杂矿用设备的关键部件检测任务中有效地解决了检测速度慢、模型体积大的问题。

To enable the coal mine equipment detection platform to accurately and rapidly identify critical components of complex mining equipment,a lightweight improved model named GhostNet-YOLOv4 based on YOLOv4 is proposed.This model introduces GhostNet as the backbone of YOLOv4’s CSPDarkNet53,which not only reduces the number of model parameters and redundant computations but also shortens the model training time.The shortcut structure in GhostNet mitigates network degradation and enhances the model's feature extraction capability.Experimental results demonstrate that the number of parameters in the improved mode is reduced by 83%compared to YOLOv4 and by 6%compared to MobileNetv3-YOLOv4,with an average recognition accuracy of 92.67%.The image detection speed can reach 33.75 frames per second,representing a 43%improvement over YOLOv4.Ghost-YOLOv4 effectively addresses the issues of slow detection speed and large model size in the task of detecting critical components of complex mining equipment.