A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks

Mark David Jenkins, Thomas Arthur Carr, Maria Insa Iglesias , Tom Buggy, Gordon Morison

Research output: Chapter in Book/Report/Conference proceedingConference contribution

169 Citations (Scopus)
675 Downloads (Pure)

Abstract

Deterioration of road and pavement surface conditions is an issue which directly affects the majority of the world today. The complex structure and textural similarities of surface cracks, as well as noise and image illumination variation makes automated detection a challenging task. In this paper, we propose a deep fully convolutional neural network to perform pixel-wise classification of surface cracks on road and pavement images. The network consists of an encoder layer which reduces the input image to a bank of lower level feature maps. This is followed by a corresponding decoder layer which maps the encoded features back to the resolution of the input data using the indices of the encoder pooling layers to perform efficient up-sampling. The network is finished with a classification layer to label individual pixels. Training time is minimal due to the small amount of training/validation data (80 training images and 20 validation images). This is important due to the lack of applicable public data available. Despite this lack of data, we are able to perform image segmentation (pixel-level classification) on a number of publicly available road crack datasets. The network was tested extensively and the results obtained indicate performance in direct competition with that of the current state-of-the-art methods.
Original languageEnglish
Title of host publication2018 26th European Signal Processing Conference (EUSIPCO)
PublisherIEEE
Pages2120-2124
Number of pages5
ISBN (Electronic)9789082797015
ISBN (Print)9781538637364
DOIs
Publication statusPublished - 2 Dec 2018
Event26th European Signal Processing Conference (EUSIPCO) - Rome, Italy
Duration: 3 Sept 20187 Sept 2018
http://www.eusipco2018.org/

Publication series

Name
ISSN (Print)2219-5491
ISSN (Electronic)2076-1465

Conference

Conference26th European Signal Processing Conference (EUSIPCO)
Country/TerritoryItaly
CityRome
Period3/09/187/09/18
Internet address

Keywords

  • image segmentation
  • task analysis
  • decoding

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks'. Together they form a unique fingerprint.

Cite this