Automatic Recognition of Patterns and Words on Road Markings Based on Laser Reflectance Information

Road surface markings provide guidance and information to drivers, promote road safety, and ensure the smooth flow of traffic. Most previous studies in this area focused on the detection and recognition of lane lines with very limited prior work on the recognition of lane center road markings. This paper focuses on the development of algorithm for automatically detecting and recognizing road markings of patterns and word messages at traffic lane center. Road markings of Chinese characters are first studied. In addition, a method for identifying the completeness of road markings is also presented. Authors propose an approach to extract road marking features based on the derivation of a binary matrix image transformed from laser reflectance collected from a top down roadway view laser scanner. The results of case studies on asphalt pavement (city streets) show that the approach can detect and recognize lane center road markings with a significant success rate. The average success rate is 96.06%, including 94.05% Chinese character road markings and 97.73% success of direction arrows and others. From the case studies, it was also noted that a significant portion of road markings have relatively low completeness. Further studies will focus on increasing survey speed, detecting other highway classes containing different Chinese characters and road markings such as icon, increasing detection rate, conducting study on various pavement condition, and developing a decision making strategy for road marking maintenance.

• 
• Supplemental Notes:
  • This paper was sponsored by TRB committee AHD55 Signing and Marking Materials.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Chou, Chia-Pei F
  • Hsu, Hung-Hsuan
  • Chen, Albert Y
  • Lee, Ning
  • Chen, Aichin
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Photos; References; Tables;
• Pagination: 14p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Case studies; Highway safety; Lane lines; Pavement maintenance; Reflectivity; Reflectorized road markings; Road markings; Traffic control devices; Urban areas
• Identifier Terms: Chinese language
• Subject Areas: Data and Information Technology; Highways; Maintenance and Preservation; Operations and Traffic Management; I60: Maintenance; I73: Traffic Control;

Filing Info

• Accession Number: 01516102
• Record Type: Publication
• Report/Paper Numbers: 14-3504
• Files: PRP, TRIS, TRB, ATRI
• Created Date: Feb 27 2014 9:06AM