Motion estimation in image sequences using the deformation of apparent contours

Abstract

The problem of determining the camera motion from apparent contours or silhouettes of curved three-dimensional surfaces is considered. In a sequence of images is shown how to use the generalized epipolar constraint on apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. Thus in theory the motion can be calculated from the deformation of a single contour. A robust algorithm for computing the motion is presented based on the maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown how to improve this estimate by maximizing the likelihood function. The algorithm has been tested on real image sequences. The result is compared to that of using only point features. The statistical evaluation shows that the technique gives accurate and stable results.