Motion Estimation from Disparity Images
A new method for 3D rigid motion estimation from stereo is proposed in this paper. The appealing feature of this method is that it directly uses the disparity images obtained from stereo matching. We assume that the stereo rig has parallel cameras and show, in that case, the geometric and topologica...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6079 |
| _version_ | 1826213375964610560 |
|---|---|
| author | Demirdjian, D. Darrell, T. |
| author_facet | Demirdjian, D. Darrell, T. |
| author_sort | Demirdjian, D. |
| collection | MIT |
| description | A new method for 3D rigid motion estimation from stereo is proposed in this paper. The appealing feature of this method is that it directly uses the disparity images obtained from stereo matching. We assume that the stereo rig has parallel cameras and show, in that case, the geometric and topological properties of the disparity images. Then we introduce a rigid transformation (called d-motion) that maps two disparity images of a rigidly moving object. We show how it is related to the Euclidean rigid motion and a motion estimation algorithm is derived. We show with experiments that our approach is simple and more accurate than standard approaches. |
| first_indexed | 2024-09-23T15:48:25Z |
| id | mit-1721.1/6079 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:48:25Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/60792019-04-11T00:13:42Z Motion Estimation from Disparity Images Demirdjian, D. Darrell, T. A new method for 3D rigid motion estimation from stereo is proposed in this paper. The appealing feature of this method is that it directly uses the disparity images obtained from stereo matching. We assume that the stereo rig has parallel cameras and show, in that case, the geometric and topological properties of the disparity images. Then we introduce a rigid transformation (called d-motion) that maps two disparity images of a rigidly moving object. We show how it is related to the Euclidean rigid motion and a motion estimation algorithm is derived. We show with experiments that our approach is simple and more accurate than standard approaches. 2004-10-04T14:37:43Z 2004-10-04T14:37:43Z 2001-05-07 AIM-2001-009 http://hdl.handle.net/1721.1/6079 en_US AIM-2001-009 1035214 bytes 158055 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Demirdjian, D. Darrell, T. Motion Estimation from Disparity Images |
| title | Motion Estimation from Disparity Images |
| title_full | Motion Estimation from Disparity Images |
| title_fullStr | Motion Estimation from Disparity Images |
| title_full_unstemmed | Motion Estimation from Disparity Images |
| title_short | Motion Estimation from Disparity Images |
| title_sort | motion estimation from disparity images |
| url | http://hdl.handle.net/1721.1/6079 |
| work_keys_str_mv | AT demirdjiand motionestimationfromdisparityimages AT darrellt motionestimationfromdisparityimages |