Temporal Surface Reconstruction
This thesis investigates the problem of estimating the three-dimensional structure of a scene from a sequence of images. Structure information is recovered from images continuously using shading, motion or other visual mechanisms. A Kalman filter represents structure in a dense depth map. Wit...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6808 |
| _version_ | 1811076435252609024 |
|---|---|
| author | Heel, Joachim |
| author_facet | Heel, Joachim |
| author_sort | Heel, Joachim |
| collection | MIT |
| description | This thesis investigates the problem of estimating the three-dimensional structure of a scene from a sequence of images. Structure information is recovered from images continuously using shading, motion or other visual mechanisms. A Kalman filter represents structure in a dense depth map. With each new image, the filter first updates the current depth map by a minimum variance estimate that best fits the new image data and the previous estimate. Then the structure estimate is predicted for the next time step by a transformation that accounts for relative camera motion. Experimental evaluation shows the significant improvement in quality and computation time that can be achieved using this technique. |
| first_indexed | 2024-09-23T10:22:02Z |
| id | mit-1721.1/6808 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:22:02Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/68082019-04-11T06:53:15Z Temporal Surface Reconstruction Heel, Joachim 3D reconstruction Kalman Filter temporal vision structuresestimation surface reconstruction This thesis investigates the problem of estimating the three-dimensional structure of a scene from a sequence of images. Structure information is recovered from images continuously using shading, motion or other visual mechanisms. A Kalman filter represents structure in a dense depth map. With each new image, the filter first updates the current depth map by a minimum variance estimate that best fits the new image data and the previous estimate. Then the structure estimate is predicted for the next time step by a transformation that accounts for relative camera motion. Experimental evaluation shows the significant improvement in quality and computation time that can be achieved using this technique. 2004-10-20T19:57:38Z 2004-10-20T19:57:38Z 1991-05-01 AITR-1296 http://hdl.handle.net/1721.1/6808 en_US AITR-1296 149 p. 23730458 bytes 8484961 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | 3D reconstruction Kalman Filter temporal vision structuresestimation surface reconstruction Heel, Joachim Temporal Surface Reconstruction |
| title | Temporal Surface Reconstruction |
| title_full | Temporal Surface Reconstruction |
| title_fullStr | Temporal Surface Reconstruction |
| title_full_unstemmed | Temporal Surface Reconstruction |
| title_short | Temporal Surface Reconstruction |
| title_sort | temporal surface reconstruction |
| topic | 3D reconstruction Kalman Filter temporal vision structuresestimation surface reconstruction |
| url | http://hdl.handle.net/1721.1/6808 |
| work_keys_str_mv | AT heeljoachim temporalsurfacereconstruction |