Cable Conduit Defect Recognition Algorithm Based on Improved YOLOv8

Abstract

The underground cable conduit system, a vital component of urban power transmission and distribution infrastructure, faces challenges in maintenance and residue detection. Traditional detection methods, such as Closed-Circuit Television (CCTV), rely heavily on the expertise and prior experience of professional inspectors, leading to time-consuming and subjective results acquisition. To address these issues and automate defect detection in underground cable conduits, this paper proposes a defect recognition algorithm based on an enhanced YOLOv8 model. Firstly, we replace the Spatial Pyramid Pooling (SPPF) module in the original model with the Atrous Spatial Pyramid Pooling (ASPP) module to capture multi-scale defect features effectively. Secondly, to enhance feature representation and reduce noise interference, we integrate the Convolutional Block Attention Module (CBAM) into the detection head. Finally, we enhance the YOLOv8 backbone network by replacing the C2f module with the base module of ShuffleNet V2, reducing the number of model parameters and optimizing the model efficiency. Experimental results demonstrate the efficacy of the proposed algorithm in recognizing pipe misalignment and residual foreign objects. The precision and mean average precision (mAP) reach 96.2% and 97.6%, respectively, representing improvements over the original YOLOv8 model. This study significantly improves the capability of capturing and characterizing defect characteristics, thereby enhancing the maintenance efficiency and accuracy of underground cable conduit systems.