A multiwindow least squares approach to the estimation of optical flow with discontinuities

The use of optical flow fields in image sequence analysis allows to perform motion-based segmentation as well as 3-D reconstruction. Many techniques for optical flow estimation are based on some global or piecewise global smoothness assumption. Other techniques compute the flow field based only on local information. In this paper a local algorithm explicitly addressing the problem of evaluating a reliable optical flow field at motion boundaries is presented. Velocity vectors are computed as solutions of a multiwindow least squares problem; the field is then regularized by a vector median filter. The algorithm is non-iterative and non-parametric. Results on both synthetic and real-world sequences are shown; a performance comparison with two well known techniques demonstrates the effectiveness of the algorithm in terms of noise rejection, motion boundary preservation and fastness.