Efficient human pose estimation from single depth images
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image without using any temporal information. The key to both approaches is the use of a large, realistic, and highly varied synthetic set of training...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 35(2013), 12 vom: 17. Dez., Seite 2821-40
|
|---|
| 1. Verfasser: |
Shotton, Jamie
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Girshick, Ross,
Fitzgibbon, Andrew,
Sharp, Toby,
Cook, Mat,
Finocchio, Mark,
Moore, Richard,
Kohli, Pushmeet,
Criminisi, Antonio,
Kipman, Alex,
Blake, Andrew |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2013
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|