Abstract
In this paper an iterative scheme is used to compute the optical flow for a sequence of images. The problem of violating the smoothness constraint is discussed and minimization of its effect is done. Also a least-squares algorithm is used to recover the motion parameters of moving camera in a fixed environment. In the case of pure translational motion, it is proved that the motion can be determined (up to a constant factor) by considering the direction of the optical flow at two points. In the same case, the relationship between the coordinates of the focus of expansion (FOE) and the motion parameters is also argued. A proposed norm based on that relationship is minimized to recover the motion parameters. Real and synthetic images are used to test the performance of the proposed technique.
Highlights
Summary
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have