Measurement of distance and height in images based on easy attainable calibration parameters

We present all image to world mapping requiring only a small and easy attainable set of parameters. The mapping provides an inverse perspective transformation, where the parameters required for the mapping can be estimated from a priori known objects or ground plane markings in the image. The world coordinate system is aligned with the projection of the optical axis onto the ground plane, in which the mapped points are assumed to lie. If no distance measurement is required the inverse perspective view can be generated by just specifying the vertical position of the horizon in the image. A modification of the basic mapping allows the determination of object heights if two corresponding vertical image coordinates are given.

[1]  A. Papoulis Signal Analysis , 1977 .

[2]  Michael A. Penna,et al.  Projective geometry and its applications to computer graphics , 1986 .

[3]  George Wolberg,et al.  Digital image warping , 1990 .

[4]  O. Faugeras Three-dimensional computer vision: a geometric viewpoint , 1993 .

[5]  Kenichi Kanatani,et al.  Geometric computation for machine vision , 1993 .

[6]  Andrew Blake,et al.  Real-time traffic monitoring , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[7]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[8]  W. von Seelen,et al.  Walking pedestrian recognition , 1999, Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383).