Vision Processing Techniques for Lane Detection and Their Fusion for Increased System Robustness

In order to enhance driver safety and ultimately enable vehicle autonomy on existing roadways, sensing techniques must be developed to determine the designated vehicle path from the roadway. This paper addresses various vision based techniques to determine drivable path on developed roadways and lane detection algorithms to facilitate path generation. These techniques carry with them a range of strengths and weaknesses such that the fusion of multiple techniques can supplement weaknesses of each other to create a more robust system. Southwest Research Institute (SwRI®) has undertaken the Southwest Safe Transport Initiative (SSTI) aimed at investigating the development and commercialization of vehicle autonomy as well as vehicle-based telemetry systems to improve safety and facilitate traffic flow. This paper will discuss the results of various vision based path detection techniques used to date in the SwRI SSTI program and their integration to provide a more robust overall path detection algorithm.

• Corporate Authors:

  ITS America

  1100 17th Street, NW, 12th Floor
  Washington, DC  United States  20036
• Authors:
  • Mentzer, Christopher
  • Kozak, Kristopher
• Conference:
  • 15th World Congress on Intelligent Transport Systems and ITS America's 2008 Annual Meeting
  • Location: New York NY, United States
  • Date: 2008-11-16 to 2008-11-20
• Publication Date: 2008

Language

• English

Media Info

• Media Type: CD-ROM
• Features: Photos; References;
• Pagination: 12p
• Monograph Title: ITS Connections: Saving Time. Saving Lives

Subject/Index Terms

• TRT Terms: Navigation; Telemetry; Traffic flow; Traffic lanes; Vehicle design; Vision
• Uncontrolled Terms: Autonomy
• Subject Areas: Data and Information Technology; Highways; Vehicles and Equipment; I91: Vehicle Design and Safety;

Filing Info

• Accession Number: 01146259
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 15 2009 3:02PM