Pavement Distress Evaluation Using 3D Depth Information from Stereo Vision

Details

• Alternative Title:
  Development of a Computer Interface and Database for the Evaluation of Pavement by the PASER Method
• Creators:
  Salari, Ezzatollah ; Chou, Eddie ; Lynch, James J.
• Corporate Creators:
  University of Toledo. Dept. of Electrical Engineering & Computer Science ; University of Detroit Mercy. Civil and Environmental Engineering
• Corporate Contributors:
  University Transportation Centers Program (U.S.)
• Subject/TRT Terms:
  Evaluation Optical Detectors Pavement Distress Research Hub Stereo Vision
• Publication/ Report Number:
  MIOH UTC TS43 2012-Final
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final report.
• Corporate Publisher:
  Michigan Ohio University Transportation Center
• Abstract:
  The focus of the current project funded by MIOH-UTC for the period 9/1/2010-8/31/2011 is to enhance our earlier effort in providing a more robust image processing based pavement distress detection and classification system. 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 images from 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, a probabilistic relaxation technique based on 3-dimensional (3D) information is proposed in this report. The primary goal of this technique is to integrate conventional image processing techniques with stereovision technology to obtain an accurate topological structure of the road defects. In addition, a road scene often contains other objects such as grass, trees, buildings which should be separated from the pavement. Therefore we have enhanced our earlier algorithm to extract the pavement region from a road scene using a Support Vector Machine (SVM). Various types of cracks are then obtained from the pavement surface images and classified using a feed-forward neural network. The proposed algorithms are implemented in MATLAB and the results are presented.
• Format:
  PDF
• Collection(s):
  University Transportation Centers US Transportation Collection
• Main Document Checksum:
  urn:sha256:7bb7a0b8c35c6ef3b0f3843edab9b13e04dc1011c2fc6627bc65c07cb5d6f1b6
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/25012/dot_25012_DS1.pdf
• File Type:
  [PDF - 4.03 MB ]