We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguit...
Abstract— This paper develops an approach for on-line segmentation of whole body human motion patterns during human motion observation and learning. A Hidden Markov Model is used...
We explore a novel motion feature as the appropriate basis for classifying or describing a number of fine motor human activities.Ourapproach not only estimates motion directions a...
Jiang Gao, Alexander G. Hauptmann, Howard D. Wactl...
When an observer moves through a rigid 3D scene, points that are near to the observer move with a different image velocity than points that are far away. The difference between im...
Michael S. Langer, Vincent Chapdelaine-Couture, Ri...
An approach for estimating the pose and motion of a known moving object in three dimensions from a sequence of monocular images is considered. The principle is to obtain initial e...