Pipeline defect classification and grading method and system based on image recognition

Abstract

The invention discloses a pipeline defect classification and grading method and system based on image recognition. The method comprises the following steps of decoding collected pipeline video or picture information; normalizing the decoded image information into image information in a standard format; forming an image set from the normalized image information, establishing an image recognition model, and performing defect feature extraction based on the image recognition model; and carrying out defect classification on the extracted defect features by utilizing a classifier, determining defect positions and associating defect levels. According to the pipeline defect classification and grading method and system based on image recognition, defect classification and grading can be automatically carried out according to the collected pipeline images, the method and system have the advantages of being high in automation level, high in detection speed and high in detection result accuracy, the labor cost is effectively saved, and the problems existing in traditional manual detection are avoided.

Description

technical field [0001] The invention relates to the technical field of municipal pipeline defect identification, in particular to a method and system for classifying and grading pipeline defects based on image recognition. Background technique [0002] During the use of the urban underground drainage network, various problems such as functional defects and structural defects of the pipes often appear, which will seriously affect the healthy operation of the drainage network and the sewage treatment of the terminal sewage plant. The traditional drainage pipeline monitoring method is to set up a camera in the drainage pipeline, and then arrange special personnel to browse the collected image information, manually find out the problem image, mark the defect category and perform defect classification. This method is slow in detection speed and extremely high in cost. , Judgment is highly subjective, defect classification and grading are greatly affected by work experience, the w...

AI Technical Summary

Problems solved by technology

The traditional drainage pipeline monitoring method is to set up a camera in the drainage pipeline, and then arrange special personnel to browse the collected image information, manually find out the problem image, mark the defect category and perform defect classification. This method is slow in detection speed and extremely high in cost. , Judgment is highly subjective, defect classification and grading are greatly affected by work experience, heavy workload, prone to omissions, slow feedback speed, and extremely low efficiency

Images