Abstract:
We present a novel application of the Expectation-Maximization algorithm to the global analysis of articulated motion. The approach utilizes a kinematic model to constrain the motion estimates, producing a segmentation of the flow field into parts with different articulated motions. Experiments with synthetic and real images are described.
copied = false, 2000);
">
@conference{Rowley-1997-14394,
author = {Henry Rowley And Jim Rehg},
title = {Analyzing Articulated Motion Using Expectation-Maximization},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {1997},
month = {June},
pages = {935 - 941},
}
author = {Henry Rowley And Jim Rehg},
title = {Analyzing Articulated Motion Using Expectation-Maximization},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {1997},
month = {June},
pages = {935 - 941},
}