• jeudi 25 mars 2004 : locaux du Département GII de l'EPUM
  
  
  • 14h00 : Applications of 2D Differential Optical Flow - Prof. John Barron
    Dept. of Computer Science
    Univ. of Western Ontario
    London, Ontario, Canada
    barron@csd.uwo.ca
    
    Résumé :
    2D optical flow is an approximation to the local image motion in a sequence of images. We first introduce 2D optical flow, show how the 2D Motion Constraint Equation results in the 2D aperture problem, describe how 2 common optical flow algorithms overcome this problem and show some optical flow computations. Then, we show 2 applications of 2D optical flow: the recovery of camera motion and scene depth from time-varying optical flow and the measurement of 2D/3D corn seedling motion and growth via 2D optical flow.