An early warning system based on Motion History Image for blind spot of oversize vehicle

Recently, because of the blind spot of oversize vehicle, accident happened repeatedly when the vehicle turned right. Therefore, to solve the problem, an embedded system based on computer vision technology which can early warn driver is proposed. Capture image with CCD camera, extract the background by using background subtraction, and build background model by the way of weighted average. After that, obtain all the moving area with MHI(Motion History Image), and sign the areas which are gathered. Then it would warn by judge whether or not the signed area in the warning area.

[1]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[3]  R. Schafer,et al.  Morphological systems for multidimensional signal processing , 1990, Proc. IEEE.

[4]  Reinhard Koch,et al.  A simple and efficient rectification method for general motion , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[6]  Zoran Zivkovic,et al.  Improved adaptive Gaussian mixture model for background subtraction , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..