Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6714Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.creator | Grauman, Kristen | - |
| dc.creator | Shakhnarovich, Gregory | - |
| dc.creator | Darrell, Trevor | - |
| dc.date | 2004-10-08T20:38:51Z | - |
| dc.date | 2004-10-08T20:38:51Z | - |
| dc.date | 2003-04-17 | - |
| dc.date.accessioned | 2013-10-09T02:46:32Z | - |
| dc.date.available | 2013-10-09T02:46:32Z | - |
| dc.date.issued | 2013-10-09 | - |
| dc.identifier | AIM-2003-008 | - |
| dc.identifier | http://hdl.handle.net/1721.1/6714 | - |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | - |
| dc.description | We present an image-based approach to infer 3D structure parameters using a probabilistic "shape+structure'' model. The 3D shape of a class of objects may be represented by sets of contours from silhouette views simultaneously observed from multiple calibrated cameras. Bayesian reconstructions of new shapes can then be estimated using a prior density constructed with a mixture model and probabilistic principal components analysis. We augment the shape model to incorporate structural features of interest; novel examples with missing structure parameters may then be reconstructed to obtain estimates of these parameters. Model matching and parameter inference are done entirely in the image domain and require no explicit 3D construction. Our shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and works even with only a single input view. Using a dataset of thousands of pedestrian images generated from a synthetic model, we can perform accurate inference of the 3D locations of 19 joints on the body based on observed silhouette contours from real images. | - |
| dc.format | 17 p. | - |
| dc.format | 6362014 bytes | - |
| dc.format | 9371703 bytes | - |
| dc.format | application/postscript | - |
| dc.format | application/pdf | - |
| dc.language | en_US | - |
| dc.relation | AIM-2003-008 | - |
| dc.subject | AI | - |
| dc.subject | 3D structure | - |
| dc.subject | statistical shape model | - |
| dc.subject | multi-view imagery | - |
| dc.subject | pose estimation | - |
| dc.title | Inferring 3D Structure with a Statistical Image-Based Shape Model | - |
| Appears in Collections: | MIT Items | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.