Name
Abstract | ||
|---|---|---|
We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the shape and appearance of the human and can be reconstructed from a sparse set of images. Similar to the human body, we also represent the image domain as SoG that models color consistent image blobs. Based on the SoG models of the image and the human body, we introduce a novel continuous and differentiable model-to-image similarity measure that can be used to estimate the skeletal motion of a human at 5 -- 15 frames per second even for many camera views. In our experiments, we show that our method, which does not rely on silhouettes or training data, offers an good balance between accuracy and computational cost. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCV.2011.6126338 | ICCV |
Keywords | Field | DocType |
image domain,skeletal motion,models color consistent image,color model,differentiable model-to-image similarity measure,articulated motion tracking,camera view,gaussians body model,computational cost,high-quality markerless motion capture,sog model,human body,gaussian processes,motion tracking,solid modeling,three dimensional | Computer vision,Motion capture,Motion field,Pattern recognition,Similarity measure,Computer science,Image processing,Artificial intelligence,Solid modeling,Frame rate,Motion estimation,Match moving | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
Citations | PageRank | References |
50 | 1.67 | 31 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Carsten Stoll | 1 | 638 | 23.05 |
| Nils Hasler | 2 | 272 | 11.28 |
| Juergen Gall | 3 | 2112 | 91.21 |
| Hans-Peter Seidel | 4 | 12532 | 801.49 |
| Christian Theobalt | 5 | 3211 | 159.16 |