1995 International Conference on Image Processing (ICIP'95) - Volume 3
Optical flow: a curve evolution approach
Washington D.C.
October 23-October 26
ISBN: 0-8186-7310-9
A. Kumar, Dept. of Aerosp. & Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
A. Tannenbaum, Dept. of Aerosp. & Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
G. Balas, Dept. of Aerosp. & Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
A novel approach for the computation of optical flow based on an L/sup 1/ type minimization is presented. It is shown that the approach has inherent advantages since it does not smooth the flow-velocity across the edges and hence preserves edge information. A numerical approach based on computation of evolving curves is proposed for computing the optical flow field and results of experiments are presented.
Index Terms:
image sequences; numerical analysis; minimisation; curve evolution; optical flow; minimization; flow velocity; edge information; numerical approach; evolving curves; optical flow field; experiments
Citation:
A. Kumar, A. Tannenbaum, G. Balas, "Optical flow: a curve evolution approach," icip, vol. 3, pp.3017, 1995 International Conference on Image Processing (ICIP'95) - Volume 3, 1995