Defect Severity Assessment Model for Sewer Pipeline Based on Automated Pipe Calibration

Abstract

To address the low-efficiency issue of the manual assessment method for sewer pipe defects, we propose a defect severity assessment model based on automated pipe calibration (DSA-APC), which can provide automated and quantitative assessments. First, the cross-section feature is extracted by automated pipe calibration. A pipe cross-section feature extraction algorithm based on restricted Hough gradient transform (RHGT) is proposed. Then, a fine-defect feature extraction method based on edge detection is proposed to extract the features of pipe defects more finely. Finally, according to the assessment standards of the sewer pipe defect, a defect severity assessment table is constructed, and the area ratio of the defect feature and cross-section feature is used to evaluate the severity. Experiments are carried out on the Songbai data set and Level-sewer10 data set. The average absolute deviation of the DSA-APC model is 2.008%, and the average accuracy is 86.73%. The experimental results show that the DSA-APC model can correctly evaluate the severity level of sewer pipe defects, which has a good practical application value. A defect severity assessment model is proposed to provide automated and quantitative assessments of the severity of sewer pipeline defects. The model uses deep learning and image processing methods to process the video and images collected from investigation robots to obtain assessment results for each pipeline. Experimenting on a real data set, the model achieved an evaluation accuracy of 86.73%. The model can automatically evaluate the defect level of the pipeline and achieve a competitive performance compared with manual evaluation. The technologies chosen for the model are practical and have been appropriately adapted and improved for the actual sewer pipeline systems, making the model both efficient and practical. The pipeline maintenance manager is able to use the model to assess and analyze the health condition of the pipeline system and develop appropriate repair plans for pipeline system problems. Although this study is specific to sewer pipeline assessment, its findings have implications for all other pipeline systems. As a new attempt, our assessment model of pipelines from a visual perspective is simple and efficient. We think that our model will have many practical applications in the field of pipeline systems.