GPU-enabled pavement distress image classification in real time

Pavement assessment is a crucial process for the maintenance of municipal roads. However, the detection of pavement distress is usually performed either manually or offline, which is not only time-consuming and subjective, but also results in an enormous amount of data being stored persistently befo...

Full description

Bibliographic Details
Main Authors: Doycheva, Kristina, Koch, Christian, König, Markus
Format: Article
Published: American Society of Civil Engineers 2016
Online Access:https://eprints.nottingham.ac.uk/35192/
_version_ 1848795024866672640
author Doycheva, Kristina
Koch, Christian
König, Markus
author_facet Doycheva, Kristina
Koch, Christian
König, Markus
author_sort Doycheva, Kristina
building Nottingham Research Data Repository
collection Online Access
description Pavement assessment is a crucial process for the maintenance of municipal roads. However, the detection of pavement distress is usually performed either manually or offline, which is not only time-consuming and subjective, but also results in an enormous amount of data being stored persistently before processing. State-of-the-art pavement image processing methods executed on a CPU are not able to analyse pavement images in real time. To compensate this limitation of the methods, we propose an automated approach for pavement distress detection. In particular, GPU implementations of a noise removal, a background correction and a pavement distress detection method were developed. The median filter and the top-hat transform are used to remove noise and shadows in the images. The wavelet transform is applied in order to calculate a descriptor value for classification purposes. The approach was tested on 1549 images. The results show that real-time pre-processing and analysis are possible.
first_indexed 2025-11-14T19:25:31Z
format Article
id nottingham-35192
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:25:31Z
publishDate 2016
publisher American Society of Civil Engineers
recordtype eprints
repository_type Digital Repository
spelling nottingham-351922020-05-04T18:00:35Z https://eprints.nottingham.ac.uk/35192/ GPU-enabled pavement distress image classification in real time Doycheva, Kristina Koch, Christian König, Markus Pavement assessment is a crucial process for the maintenance of municipal roads. However, the detection of pavement distress is usually performed either manually or offline, which is not only time-consuming and subjective, but also results in an enormous amount of data being stored persistently before processing. State-of-the-art pavement image processing methods executed on a CPU are not able to analyse pavement images in real time. To compensate this limitation of the methods, we propose an automated approach for pavement distress detection. In particular, GPU implementations of a noise removal, a background correction and a pavement distress detection method were developed. The median filter and the top-hat transform are used to remove noise and shadows in the images. The wavelet transform is applied in order to calculate a descriptor value for classification purposes. The approach was tested on 1549 images. The results show that real-time pre-processing and analysis are possible. American Society of Civil Engineers 2016-07-19 Article PeerReviewed Doycheva, Kristina, Koch, Christian and König, Markus (2016) GPU-enabled pavement distress image classification in real time. Journal of Computing in Civil Engineering . ISSN 1943-5487 (In Press)
spellingShingle Doycheva, Kristina
Koch, Christian
König, Markus
GPU-enabled pavement distress image classification in real time
title GPU-enabled pavement distress image classification in real time
title_full GPU-enabled pavement distress image classification in real time
title_fullStr GPU-enabled pavement distress image classification in real time
title_full_unstemmed GPU-enabled pavement distress image classification in real time
title_short GPU-enabled pavement distress image classification in real time
title_sort gpu-enabled pavement distress image classification in real time
url https://eprints.nottingham.ac.uk/35192/