Name
Abstract | ||
|---|---|---|
We propose a novel clustering scheme for spatio-temporal segmentation of sparse motion fields obtained from feature tracking. The approach allows for the segmentation of meaningful motion components in a scene, such as short- and long-term motion of single objects, groups of objects and camera motion. The method has been developed within a project on the analysis of low-quality archive films. We qualitatively and quantitatively evaluate the performance and the robustness of the approach. Results show, that our method successfully segments the motion components even in particularly noisy sequences. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-11301-7_44 | MMM |
Keywords | Field | DocType |
single object,noisy sequence,motion component,feature tracking,spatio-temporal segmentation,novel trajectory,sparse motion field,low-quality archive film,camera motion,meaningful motion component,long-term motion,motion segmentation | Structure from motion,Computer vision,Scale-space segmentation,Motion field,Pattern recognition,Computer science,Segmentation,Robustness (computer science),Artificial intelligence,Motion estimation,Cluster analysis,Match moving | Conference |
Volume | ISSN | ISBN |
5916 | 0302-9743 | 3-642-11300-1 |
Citations | PageRank | References |
6 | 0.48 | 12 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Matthias Zeppelzauer | 1 | 186 | 21.35 |
| Maia Zaharieva | 2 | 121 | 14.62 |
| Dalibor Mitrovic | 3 | 76 | 6.23 |
| Christian Breiteneder | 4 | 410 | 288.17 |