Fully Automatic Roadside Camera Calibration for Traffic Surveillance

This paper deals with automatic calibration of roadside surveillance cameras. The authors focus on parameters necessary for measurements in traffic surveillance applications. Contrary to the existing solutions, this approach requires no a priori knowledge, and it works with a very wide variety of road settings (number of lanes, occlusion, quality of ground marking), as well as with practically unlimited viewing angles. The main contribution is that this solution works fully automatically -- without any per-camera or per-video manual settings or input whatsoever -- and it is computationally inexpensive. The authors approach uses tracking of local feature points and analyzes the trajectories in a manner based on cascaded Hough transform and parallel coordinates. An important assumption for the vehicle movement is that at least a part of the vehicle motion is approximately straight -- the authors discuss the impact of this assumption on the applicability of the approach and show experimentally that this assumption does not limit the usability of the approach severely. The authors efficiently and robustly detect vanishing points, which define the ground plane and vehicle movement, except for the scene scale. The algorithm also computes parameters for radial distortion compensation. Experiments show that the obtained camera parameters allow for measurements of relative lengths (and potentially speed) with ~2% mean accuracy. The processing is performed easily in real time, and typically, a 2-min-long video is sufficient for stable calibration.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01574963
  • Record Type: Publication
  • Files: TLIB, TRIS
  • Created Date: Aug 5 2015 12:32PM