We present a method for improving robustness in feature-based tracking of human motion. Motion flows of features estimated by a standard tracker are modified to be coherent with neighboring ones. This coherence constraint is computed based on a smooth approximation to initial motion flows computed by the tracker. With these tracking results, we demonstrate motion segmentation of different body parts in an image sequence
Type
conference paper
Authors
Publication date
2003
Publisher
Published in
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing
Volume
3
Start page
29
End page
32
Note
CVlab, Lausanne, Switzerland
Peer reviewed
REVIEWED
Available on Infoscience
January 16, 2007
Use this identifier to reference this record