z-logo
open-access-imgOpen Access
A Novel Approach to Motion Segmentation
Author(s) -
D. Sinclair,
Andrew Blake,
Paul Beardsley,
David W. Murray
Publication year - 1991
Publication title -
citeseer x (the pennsylvania state university)
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.5.54
Subject(s) - computer science , computer vision , artificial intelligence , segmentation , motion (physics) , image segmentation
This paper offers a novel means of segmenting independently moving objects from rigid backgrounds. The camera motion can be arbitrary with the proviso that independently moving objects are not moving parallel to it. A new method of treating visual motion is presented. The method relies on describing the motion of points in the world in terms of their angular velocity relative to the camera. In the case of a static scene the method permits the recovery of the direction of camera motion and the camera's angular velocity from the optical flow and its first derivatives at only three points.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom