Abstract | ||
---|---|---|
A robust VAR-based (vector autoregressive) model is in- troduced for motion prediction in 3D hand tracking. This dynamic VAR motion model is learned in an online man- ner. The kinematic structure of the hand is accounted for in the form of constraints when solving for the parameters of the VAR model. Also integrated into the motion prediction model are adaptive weights that are optimised according to the reliability of past predictions. Experiments on synthetic and real video sequences show a substantial improvement in tracking performance when the robust VAR motion model is used. In fact, utilising the robust VAR model allows the tracker to handle fast out-of-plane hand movement with se- vere self-occlusion. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/AFGR.2008.4813414 | Amsterdam |
Keywords | DocType | ISSN |
autoregressive processes,image sequences,object detection,tracking,video signal processing,3D hand tracking,adaptive VAR model,dynamic VAR motion model,motion prediction model,vector autoregressive,video sequences | Conference | 2326-5396 |
ISBN | Citations | PageRank |
978-1-4244-2154-1 | 1 | 0.36 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Desmond Chik | 1 | 1 | 0.36 |
Jochen Trumpf | 2 | 208 | 24.16 |
Nicol N. Schraudolph | 3 | 1185 | 164.26 |