Road Distress Analysis using 2D and 3D Information

Road Distress Analysis using 2D and 3D Information

Bibliographic Details
Main Author: Bao, Guanqun
Language:English
Published: University of Toledo / OhioLINK 2010
Subjects:
Electrical Engineering
pavement inspection
stereo vision
neural network
segmentation
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=toledo1289874675
id ndltd-OhioLink-oai-etd.ohiolink.edu-toledo1289874675
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-toledo12898746752021-08-03T06:07:48Z Road Distress Analysis using 2D and 3D Information Bao, Guanqun Electrical Engineering pavement inspection stereo vision neural network segmentation During the last few decades, many efforts have been made to produce automatic inspection systems to meet the specific requirements in assessing distress on the road surfaces using video cameras and image processing algorithms. However, due to the noisy pavement surfaces, limited success was accomplished. One major issue with pure video based systems is their inability to discriminate dark areas not caused by pavement distress such as tire marks, oil spills, shadows, and recent fillings. To overcome the limitation of the conventional imaging based methods, novel pavement inspection approaches based on both 2-dimensional (2D) and 3-dimensional (3D) information are proposed in this thesis. Techniques such as 2D feature extraction, morphological operations, artificial neural networks, and 3D model reconstruction are utilized successively within the research. The primary goal of this study is to integrate conventional image processing techniques with stereovision technology to provide a full dimensional visualization of the pavement surface. With segmentation results from the 2D images and depth information estimated by 3D reconstruction, the detailed topological structure of the road defects can be accurately obtained. Simulation results show the proposed system is effective and robust on a variety of pavement surfaces. 2010 English text University of Toledo / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=toledo1289874675 http://rave.ohiolink.edu/etdc/view?acc_num=toledo1289874675 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
collection NDLTD
language English
sources NDLTD
topic Electrical Engineering
pavement inspection
stereo vision
neural network
segmentation
spellingShingle Electrical Engineering
pavement inspection
stereo vision
neural network
segmentation
Bao, Guanqun
Road Distress Analysis using 2D and 3D Information
author Bao, Guanqun
author_facet Bao, Guanqun
author_sort Bao, Guanqun
title Road Distress Analysis using 2D and 3D Information
title_short Road Distress Analysis using 2D and 3D Information
title_full Road Distress Analysis using 2D and 3D Information
title_fullStr Road Distress Analysis using 2D and 3D Information
title_full_unstemmed Road Distress Analysis using 2D and 3D Information
title_sort road distress analysis using 2d and 3d information
publisher University of Toledo / OhioLINK
publishDate 2010
url http://rave.ohiolink.edu/etdc/view?acc_num=toledo1289874675
work_keys_str_mv AT baoguanqun roaddistressanalysisusing2dand3dinformation
_version_ 1719431382398140416

Similar Items