1 June 1993 Multiwindow least-squares approach to the estimation of optical flow with discontinuities
Author Affiliations +
The use of optical flow fields in image sequence analysis allows us 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. 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 noniterative and nonparametric. 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 speed.
Franco Bartolini, Franco Bartolini, Vito Cappellini, Vito Cappellini, Carlo Colombo, Carlo Colombo, Alessandro Mecocci, Alessandro Mecocci, } "Multiwindow least-squares approach to the estimation of optical flow with discontinuities," Optical Engineering 32(6), (1 June 1993). https://doi.org/10.1117/12.134199 . Submission:

Back to Top