重庆理工大学学报(自然科学) ›› 2023, Vol. 37 ›› Issue (4): 235-244.

• 电气·电子 • 上一篇    下一篇

一种改进 YOLOv5s的自爆绝缘子检测算法研究

王红君,王金云,赵 辉   

  1. (1.天津理工大学 天津市复杂系统控制理论与应用重点实验室,天津 300384; 2.天津农学院 工程技术学院,天津 300392)
  • 出版日期:2023-05-06 发布日期:2023-05-06
  • 作者简介:王红君,女,教授,硕士生导师,主要从事图形图像处理、复杂系统智能控制理论及应用、电力系统及其自动化研 究,Email:hongewang@126.com;通信作者 王金云,女,硕士研究生,主要从事目标检测、电力巡检研究,Email: jyun0628@163.com。

Research on an improved YOLOv5s self-exploding insulator detection algorithm

  • Online:2023-05-06 Published:2023-05-06

摘要: 针对绝缘子缺陷巡检过程中,传统算法因背景复杂难以同时兼顾检测精度与模型 大小的问题,提出一种基于改进 YOLOv5s的绝缘子缺陷检测模型。首先,采用 BottleneckCSP 结构,引入轻量型空间与通道卷积注意力机制,强化绝缘子特征并抑制复杂背景特征;然后,提 出一种改进的 BiFPN结构,实现多尺度特征融合,提升小目标检测能力;最后,采用 Kmeans++ 算法重新聚类先验框,并设计轻量型 GhostC3和 GhostConv模块,保证网络精度的同时减小模 型大小。实验结果表明:改进算法在 Insulator2022数据集上的 mAP值达到 92.3%,提升了 36%,参数量减少了 26.73%,浮点运算量减少了 23.17%,漏检率降低了 5.47%;在公开数据 集上,缺陷绝缘子 mAP值达到 99.5%,各项评估指标值优于 FasterRCNN、SSD、YOLOv3和 YOLOv3tiny主流算法以及绝缘子检测相关算法。

关键词: 绝缘子缺陷, 目标检测, YOLOv5s算法, 改进 BiFPN, 轻量化网络

Abstract: In the process of insulator defect inspection, it is difficult for traditional algorithms to take into account of detection accuracy and model size at the same time due to complex background. In this paper, an insulator defect detection model based on improved YOLOv5s is proposed. Firstly, a Bottleneck CSP structure and an attention mechanism of lightweight spatial and channel convolution are used to strengthen insulator characteristics and suppress the complex background characteristics. Secondly, an improved BiFPN structure is proposed to achieve multi-scale feature fusion and improve the ability of small object detection. Finally, K-means++ algorithm is used to re-cluster the prior frames, and lightweight GhostC3 and Ghost Conv modules are designed to ensure accuracy of the network and reduce size of the model. The experimental results show that the mAP of the improved algorithm in this paper reaches 92.3% in Insulator2022 dataset, with an increase of 3.6%; the number of parameters reduces by 26.73%, the floating point arithmetic reduces by 23.17%, and the missed detection rate reduces by 5.47%. In the open dataset, the defective insulator mAP reaches 99.5%. All of the evaluation index values are better than those of the mainstream algorithms of Faster-RCNN, SSD, YOLOv3 and YOLOv3-tiny as well as the related algorithms of insulator detection.

中图分类号: 

  • TP391.4