Name
Abstract | ||
|---|---|---|
Recent algorithms for monocular motion capture (MoCap) estimate weak-perspective camera matrices between images using a small subset of approximately-rigid points on the human body (i.e.\ the torso and hip). A problem with this approach, however, is that these points are often close to coplanar, causing canonical linear factorisation algorithms for rigid structure from motion (SFM) to become extremely sensitive to noise. In this paper, we propose an alternative solution to weak-perspective SFM based on a convex relaxation of graph rigidity. We demonstrate the success of our algorithm on both synthetic and real world data, allowing for much improved solutions to marker less MoCap problems on human bodies. Finally, we propose an approach to solve the two-fold ambiguity over bone direction using a k-nearest neighbour kernel density estimator. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/DICTA.2011.87 | Digital Image Computing Techniques and Applications |
Keywords | Field | DocType |
bone direction,graph rigidity,approximately-rigid point,estimate weak-perspective camera matrix,near-coplanar structure,alternative solution,monocular motion,convex relaxation,human body,canonical linear factorisation algorithm,mocap problem,structure from motion,graph theory,noise,approximation theory,edge detection,kernel density estimate,estimation theory,motion capture,pose estimation,three dimensional,coplanar,torso | Structure from motion,Graph theory,Motion capture,Computer vision,Matrix (mathematics),Computer science,Approximation theory,Pose,Artificial intelligence,Estimation theory,Kernel density estimation | Conference |
ISBN | Citations | PageRank |
978-1-4577-2006-2 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jack Valmadre | 1 | 466 | 14.08 |
| Ben Upcroft | 2 | 357 | 34.85 |
| Sridha Sridharan | 3 | 2092 | 222.69 |
| Simon Lucey | 4 | 2034 | 116.77 |