Insulator Defect Detection Based on the CDDCR–YOLOv8 Algorithm

Abstract

Abstract Insulator defect detection is a critical aspect of grid inspection in reality, yet it faces intricate environmental challenges, such as slow detection speed and low accuracy. To address this issue, we propose a YOLOv8-based insulator defect detection algorithm named CDDCR–YOLOv8. This algorithm divides the input insulator images into multiple grid cells, with each grid cell responsible for predicting the presence and positional information of one or more targets. First, we introduce the Coordinate Attention (CA) mechanism module into the backbone network and replace the original C2f module with the enhanced C2f_DCN module. Second, improvements are made to the original upsampling and downsampling layers in the neck network, along with the introduction of the lightweight module RepGhost. Finally, we employ Wise-IoU (WIoU) to replace the original CIoU as the loss function for network regression. Experimental results demonstrate that the improved algorithm achieves an average precision mean (mAP @ 0.5) of 97.5% and 90.6% on the CPLID and IPLID data sets, respectively, with a frame per second (FPS) of 84, achieving comprehensive synchronous improvement. Compared to traditional algorithms, our algorithm exhibits significant performance enhancement.

Keywords

• Object detection
• Insulator defect detection
• YOLOv8
• Attention mechanism