File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Articulated structure from motion through ellipsoid fitting
Title | Articulated structure from motion through ellipsoid fitting |
---|---|
Authors | |
Keywords | Non-rigid structure from motion Articulated structure Ellipsoid fitting Motion segmentation Orthographic camera |
Issue Date | 2015 |
Citation | The 19th International Conference on Image Processing, Computer Vision and Pattern Recognition (IPCV’15), Las Vegas, NV., 27-30 July 2015. In Conference Proceedings, 2015, p. 179-185 How to Cite? |
Abstract | We present a new method to reconstruct non-rigid objects from orthographic projections based on the assumption of articulated model. We introduce an ellipsoid property to identify points belonging to a rigid subset. This enables us to formulate the problem of motion segmentation as an ellipsoid fitting problem. The obtained rigid subsets are then linked as kinematic chains to constitute 3D articulated structure. This method is practical of computational complexity O(N) mainly based on linear least squares. We demonstrate the effectiveness of this method through experiments on real tracking data, motion capture data, and challenging human dataset with missing data, in comparison with existing methods. |
Description | IPCV'15 is among the conferences of WORLDCOMP 2015 |
Persistent Identifier | http://hdl.handle.net/10722/214829 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, PB | - |
dc.contributor.author | Hung, YS | - |
dc.date.accessioned | 2015-08-21T11:57:52Z | - |
dc.date.available | 2015-08-21T11:57:52Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | The 19th International Conference on Image Processing, Computer Vision and Pattern Recognition (IPCV’15), Las Vegas, NV., 27-30 July 2015. In Conference Proceedings, 2015, p. 179-185 | - |
dc.identifier.uri | http://hdl.handle.net/10722/214829 | - |
dc.description | IPCV'15 is among the conferences of WORLDCOMP 2015 | - |
dc.description.abstract | We present a new method to reconstruct non-rigid objects from orthographic projections based on the assumption of articulated model. We introduce an ellipsoid property to identify points belonging to a rigid subset. This enables us to formulate the problem of motion segmentation as an ellipsoid fitting problem. The obtained rigid subsets are then linked as kinematic chains to constitute 3D articulated structure. This method is practical of computational complexity O(N) mainly based on linear least squares. We demonstrate the effectiveness of this method through experiments on real tracking data, motion capture data, and challenging human dataset with missing data, in comparison with existing methods. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV) | - |
dc.relation.ispartof | WORLDCOMP 2015 | - |
dc.subject | Non-rigid structure from motion | - |
dc.subject | Articulated structure | - |
dc.subject | Ellipsoid fitting | - |
dc.subject | Motion segmentation | - |
dc.subject | Orthographic camera | - |
dc.title | Articulated structure from motion through ellipsoid fitting | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Hung, YS: yshung@hkucc.hku.hk | - |
dc.identifier.authority | Hung, YS=rp00220 | - |
dc.identifier.hkuros | 249773 | - |
dc.identifier.hkuros | 250746 | - |
dc.identifier.spage | 179 | - |
dc.identifier.epage | 185 | - |