Semantic segmentation of sewer pipe defects using deep dilated convolutional neural network

M. Z. Wang, J. C.P. Cheng

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

14 Citations (Scopus)

Abstract

Semantic segmentation of closed-circuit television (CCTV) images can facilitate automatic severity assessment of sewer pipe defects by assigning defect labels to each pixel in the image, from which defect types, locations and geometric information can be obtained. In this study, a deep convolutional neural network (CNN), namely DilaSeg, is developed based on dilated convolution for improving the segmentation of sewer pipe defects including cracks, tree root intrusion and deposit. Sewer pipe CCTV images are extracted from inspection videos and are annotated to be used as the ground truth labels for training the model. DilaSeg is constructed with dilated convolution for producing feature maps with high resolution. Both DilaSeg and the state-of-the-art model, fully convolutional network (FCN), are trained and evaluated on the annotated dataset using the same hyper-parameters. The results of the experiments indicate that the proposed DilaSeg improved the segmentation accuracy significantly compared with FCN, with 18% of increase in mean pixel accuracy (mPA) and 22% of increase in mean intersection over union (IoU) with a fast detection speed. © 2019 International Association for Automation and Robotics in Construction I.A.A.R.C. All rights reserved.
Original languageEnglish
Title of host publicationProceedings of the 36th International Symposium on Automation and Robotics in Construction, ISARC 2019
PublisherInternational Association for Automation and Robotics in Construction I.A.A.R.C)
Pages586-594
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event36th International Symposium on Automation and Robotics in Construction, ISARC 2019 - Banff, Canada
Duration: 21 May 201924 May 2019

Publication series

NameProceedings of the 36th International Symposium on Automation and Robotics in Construction, ISARC 2019

Conference

Conference36th International Symposium on Automation and Robotics in Construction, ISARC 2019
PlaceCanada
CityBanff
Period21/05/1924/05/19

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

  • Convolutional neural network (CNN)
  • Defect segmentation
  • Dilated convolution
  • Semantic segmentation
  • Sewer pipe defect
  • Visual inspection

Fingerprint

Dive into the research topics of 'Semantic segmentation of sewer pipe defects using deep dilated convolutional neural network'. Together they form a unique fingerprint.

Cite this