Analysis of Contour Motions
Liu, Ce, Freeman, William T., Adelson, Edward H.
–Neural Information Processing Systems
A reliable motion estimation algorithm must function under a wide range of conditions. Oneregime, which we consider here, is the case of moving objects with contours but no visible texture. Tracking distinctive features such as corners can disambiguate the motion of contours, but spurious features such as T-junctions can be badly misleading. It is difficult to determine the reliability of motion from local measurements, since a full rank covariance matrix can result from both real and spurious features. We propose a novel approach that avoids these points altogether, andderives global motion estimates by utilizing information from three levels of contour analysis: edgelets, boundary fragments and contours.
Neural Information Processing Systems
Dec-31-2007
- Country:
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.14)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (0.93)
- Vision (1.00)
- Information Technology > Artificial Intelligence