Manual defect identification and classification for sewer pipes using footage from closed-circuit television (CCTV) monitoring is generally time-consuming and can have varying degrees of accuracy depending on the expertise of the technologist conducting the analysis. In order to address this issue, automation is proposed as an alternative to human visual inspection and consists of extracting still frames from collected videos, examining whether these frames include defects, and finally classifying these defects into different types (e.g., cracks or fractures). A classifier based on a new convolutional neural network, called You only look once (YOLO), is proposed in this paper which consists of four parts: (1) extracting the colour frames including defects from the video; (2) transferring information in the selected frames in order to highlight the part of the image containing the defect; (3) using the training images with the corresponding information as inputs to generate a classifier by means of the YOLO network; and (4) testing performance of the automatic classifier based on the images for validation. The proposed framework is then applied to a case study of the City of Edmonton in order to automatically detect the number and location of defects in sewer pipes to facilitate improved productivity for human visual defect identification and human resource allocation. The results show that the YOLO-based classifier performs accurately: up to 96% accuracy in automated defect detection, although some mistakes occurred such as mix-up other type of defect.
|Publication status||Published - 2019|
|Event||2019 Canadian Society for Civil Engineering Annual Conference, CSCE 2019 - Sheraton Laval and Convention Centre, Laval, Canada|
Duration: 12 Jun 2019 → 15 Jun 2019
|Conference||2019 Canadian Society for Civil Engineering Annual Conference, CSCE 2019|
|Abbreviated title||CSCE 2019|
|Period||12/06/19 → 15/06/19|