Sewer Pipeline Defect Detection based on YOLOv8-CPA

As the service life of sewer pipelines increases, various types of defects inevitably occur, posing significant risks to urban infrastructure and public safety. Timely detection and assessment of these defects are crucial to ensuring the structural integrity and functionality of sewer systems. Traditional manual inspections are time-consuming, laborintensive, and prone to human errors. Object detection technology based on deep learning provides an efficient and automated alternative by training models to accurately identify the type and location of pipeline defects. However, the complex internal environment of pipelines, including low-light conditions, noise interference, and varying defect appearances, presents significant challenges for detection accuracy. To address these issues, we conducted an in-depth study on common sewer pipeline defects and applied image preprocessing techniques such as grayscale conversion and denoising to enhance dataset quality. Furthermore, we improved the YOLOv8 model by integrating the CPA Enhancer module into its Backbone structure, optimizing feature extraction and defect recognition. Based on this enhancement, we developed a deep active learning framework, YOLOv8-CPA, which leverages a chain-thinking prompt mechanism to refine detection performance iteratively. Experimental results demonstrate that the YOLOv8-CPA pipeline inspection system achieves high accuracy in detecting and classifying pipeline defects. By improving detection efficiency, ensuring consistency, and accelerating validation processes, our system significantly enhances the sewer inspection workflow. The proposed method contributes to effective defect management, aiding in the timely implementation of appropriate maintenance and rehabilitation strategies for sewer infrastructure.