Gonzalez, J. J.Ik Soo, LimFua, P.Thalmann, D.2007-01-162007-01-162007-01-16200310.1109/ICASSP.2003.1199099https://infoscience.epfl.ch/handle/20.500.14299/239191We 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 sequencefeature extractionimage segmentationimage sequencesoptical trackingtext::conference output::conference proceedings::conference paper