Name
Abstract | ||
|---|---|---|
We present a method for estimating pose information from a single depth image given an arbitrary kinematic structure without prior training. For an arbitrary skeleton and depth image, an evolutionary algorithm is used to find the optimal kinematic configuration to explain the observed image. Results show that our approach can correctly estimate poses of 39 and 78 degree-of-freedom models from a single depth image, even in cases of significant self-occlusion. |
Year | Venue | Keywords |
|---|---|---|
2011 | CoRR | artificial intelligent,evolutionary algorithm,degree of freedom,pattern recognition,pose estimation |
Field | DocType | Volume |
Computer vision,Kinematics,Evolutionary algorithm,Pattern recognition,Computer science,3D pose estimation,Pose,Artificial intelligence,Machine learning | Journal | abs/1106.5341 |
Citations | PageRank | References |
5 | 0.54 | 7 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Le Ly | 1 | 34 | 2.38 |
| Ashutosh Saxena | 2 | 4575 | 227.88 |
| Hod Lipson | 3 | 3161 | 225.54 |