Abstract | ||
---|---|---|
Accurate markerless motion capture systems rely on images that allow segmentation of the person in the foreground. While the accuracy of such approaches is comparable to marker based systems, the segmentation step makes strong restrictions to the capture environment, e.g. homogenous clothing or background, constant lighting etc. In our approach a template model is fitted to images by an Analysis-by-Synthesis method, which doesn't need explicit segmentation or homogenous clothing and gives reliable results even with non-static cluttered background. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11861898_58 | DAGM-Symposium |
Keywords | Field | DocType |
capture environment,explicit segmentation,point tracking,monocular body,strong restriction,homogenous clothing,non-static cluttered background,color histogram,constant lighting etc.,accurate markerless motion capture,segmentation step,reliable result,analysis-by-synthesis method,pose estimation,motion capture,analysis by synthesis | Computer vision,Motion capture,Scale-space segmentation,Computer science,Segmentation,Image processing,Image segmentation,Pose,Artificial intelligence,Motion estimation,Monocular | Conference |
Volume | ISSN | ISBN |
4174 | 0302-9743 | 3-540-44412-2 |
Citations | PageRank | References |
3 | 0.42 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Grest | 1 | 129 | 10.65 |
Dennis Herzog | 2 | 3 | 0.42 |
Reinhard Koch | 3 | 2038 | 170.17 |