Realtime Lane Tracking of Curved Local Road

Motivation & Approach

  • For collision warning system: need to know the lane curvature in urban environment.
  • Realtime processing required.
  • Left and right boundaries are separately represented by cubic-spline curves.
  • RANSAC (RANdom SAmple Concensus) for fast grouping of lane markings.
  • Particle filtering for robust tracking.
  • Probabilistic reasoning to handle emerging/merging/splitting/disappearing lane boundaries in a unified framework.
    		•

    Experimental Data and Results

    Video clips (IEEE Trans. ITS):

    Video #1

  • [Raw video clip (in MPEG)], [Result video clip (in AVI)]
  • First 3100 frames (cargo scenes) were skipped in the result video. 10 frames per sec (the result video is in 3x speed).
  • Calibration information: image coord (pixel) => world coord (meter):
    (224,194) => (0, 8), (347,196) => (3, 8), (249,135) => (0, 30), (285,136) => (3, 30)

    • Video #2 (night)

  • [Raw video clip (in MPEG)], [Result video clip (in AVI)]
  • Same calibration was used as above

    • Video #3 (higher resolution)

  • [Raw video clip (in MPEG)], [Result video clip (in AVI)]
  • Detection without tracking: [r0913021-detection.avi], and the result by the CHEVP algorithm (for comparison): [r0913021-chevp.avi]
  • Calibration information: image coord (pixel) =>world coord (meter):
    (96,148) => (0, 8), (343,152) => (3, 8), (147,31) => (0, 30), (218,33) => (3, 30)

    • Publications

  • Z. Kim, "Robust Lane Detection and Tracking in Challenging Scenarios," IEEE Trans. on Intelligent Transportation Systems, vol. 9, no. 1, pp. 16-26, 2008. [PDF]
  • Z. Kim, "Realtime Lane Tracking of Curved Local Roads", IEEE Intelligent Transportation Systems Conference, pp. 1149-1155, 2006. [PDF]

    • [Home]

    Disclaimer on IEEE publications: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
    IEEE material: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.