一种结合语义分割和目标检测的级联式绝缘子缺陷检测方法

A Cascaded Insulator Defect Detection Model Combining Semantic Segmentation and Object Detection

绝缘子缺陷检测是变电站日常巡检的重要部分。由于变电站内环境复杂,绝缘子缺陷检测易受到背景因素干扰。因此,本文提出一种结合语义分割和目标检测的级联式绝缘子缺陷检测模型。该模型由绝缘子分割、绝缘子裁减、缺陷检测3个模块组成。绝缘子分割模块将绝缘子从复杂的环境中分离并提出一种边缘增强的损失函数;绝缘子裁减模块利用图像处理方法获得轴对齐的绝缘子区域;缺陷检测模块完成缺陷的检测。实验结果表明,级联式绝缘子缺陷检测模型的整体准确率为60.63%。其中,边缘加权的Unet对绝缘子的分割准确率达到83.99%,锚框改进的RetinaNet对缺陷的检测准确率达到63.32%。与单级绝缘子缺陷检测模型对比分析,所提出的级联式绝缘子缺陷检测模型可有效地去除环境因素干扰,检测出大部分的绝缘子缺陷区域。

Insulator defect detection is an important part of the routine inspection of substations.Using the video surveillance im⁃ages in the substation,we propose a cascaded insulator defect detection model that combines semantic segmentation with object detection aiming at the low detection accuracy of the insulator defect detection model.The model consists of three modules:Insu⁃lator segmentation,insulator cutting and defect detection.The insulator segmentation module separates the insulator from the complex environment and proposes an edge enhancement loss function.The insulator cutting module uses the image processing method to obtain the insulator region aligned with the axis.The defect detection module completes the defect detection.Experi⁃ment results show that the accuracy of edge-enhanced Unet for insulator segmentation reaches 83.99%,and the accuracy of Reti⁃naNet with improved anchor generation method for defect detection reaches 63.32%.Compared with the single-stage insulator de⁃fect detection model,the proposed cascade insulator defect detection model can effectively eliminate the interference of environ⁃ment,detecting most of the insulator defects.