Details:

Creators:
Chou, Eddie Y. ; Salari, Ezzatollah
Chou, Eddie Y. ; Salari, Ezzatollah Less -
Corporate Creators:
University of Toledo. University Transportation Center
Corporate Contributors:
United States. Department of Transportation. University Transportation Centers (UTC) Program
Subject/TRT Terms:
[+]
Highway Facilities Roads Transportation, Hydraulic And Utility Facilities
Resource Type:
Tech Report
Geographical Coverage:
Ohio
Corporate Publisher:
University of Toledo. University Transportation Center
Abstract:
One of the most important tasks in maintaining transportation facilities such as highways

and streets is the evaluation of the existing condition. Visual evaluation by human

inspectors is subjective in nature, therefore has issues of consistency and the speed and

frequency of evaluation is limited due to the manual process. Automated evaluation

using modern digital image processing and pattern recognition techniques can increase

the efficiency and accuracy and decrease the costs of condition evaluation. Several

automated condition evaluation systems have been developed, but these systems

commonly require special devices such as strobe light, laser beams, etc, which increase

the cost and limit the system to certain applications. In this study, a low cost automatic

pavement distress evaluation approach is presented. This method can provide real-time

pavement distress detection as well as evaluation results based on color images captured

from a camera installed on a survey vehicle. The entire process consists of two main

parts: pavement surface extraction followed by pavement distress detection and

classification. In the first part, a novel color segmentation method based on a feed

forward neural network is employed to separate the road surface from the background.

In the second part, a segmentation technique based on probabilistic relaxation is used to

separate distress areas from the road surface. The geometrical parameters obtained from

the detected distresses are then fed to a neural network based pavement distress classifier

in which the defects are classified into different types. Simulation results are given to

show that the scheme presented in this report is both effective and reliable on a variety of

pavement images.


Format:
PDF
Collection(s):
US Transportation Collection University Transportation Centers
Main Document Checksum:
[+]
urn:sha256:cfbdbcb057d97ba0e3a1f6c81ee6b49b7d93c4e3e4f960636f88567cf1647378
Download URL:
https://rosap.ntl.bts.gov/view/dot/24092/dot_24092_DS1.pdf
File Type:

Supporting Files

• No Additional Files

More +