In this report, the authors present a novel approach for estimating traffic speed using a sequence of images from an uncalibrated camera. They assert that exact calibration is not necessary to estimate speed. Instead, to estimate speed, they use: (1) geometric relationships inherently available in the image, (2) some common sense assumptions that reduce the problem to 1-dimensional geometry, (3) frame differencing to isolate moving edges and track vehicles between frames, and (4) parameters from the distribution of vehicle lengths.
May 4, 2007
Daniel J. Dailey, Fredrick W. Cathey, Suree Pumrin.
Washington State Transportation Center (TRAC)
- # of Pages: 29 p., 357 KB (PDF)
- Subject: Calibration, Cameras, Closed circuit television, Estimating, Image processing, Traffic speed.
- Keywords: Video image processing, calibration, camera, speed sensor, traffic flow, vehicle length distribution.
- Related Publications:
This abstract was last modified April 29, 2008