Motion estimation in image sequences using the deformation of apparent contours

The problem of determining the camera motion from apparent contours or silh ouettes of a priori unknown curved three-dimensional surfaces is considered . In a sequence of images, it is shown how to use the generalized epipolar constraint an apparent contours. One such constraint is obtained for each e pipolar tangency point in each image pair. An accurate algorithm for comput ing the motion is presented based on a maximum likelihood estimate. It is s hown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown that in theory the motion can be calcula ted from the deformation of a single contour. The algorithm has been tested on several real image sequences, for both Euclidean and protective reconst ruction. The resulting motion estimate is compared to motion estimates calc ulated independently using standard feature-based methods. The motion estim ate is also used to classify the silhouettes as curves or apparent contours . This is a strong indication that the motion estimate is of good quality. The statistical evaluation shows that the technique gives accurate and stab le results.