Recognizing 3D Ojbects of 2D Images: An Error Analysis
Many object recognition systems use a small number of pairings of data and model features to compute the 3D transformation from a model coordinate frame into the sensor coordinate system. With perfect image data, these systems work well. With uncertain image data, however, their performance is...
| Main Authors: | , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5959 |
| _version_ | 1811093392412639232 |
|---|---|
| author | Grimson, W. Eric Huttenlocher, Daniel P. Alter, T. D. |
| author_facet | Grimson, W. Eric Huttenlocher, Daniel P. Alter, T. D. |
| author_sort | Grimson, W. Eric |
| collection | MIT |
| description | Many object recognition systems use a small number of pairings of data and model features to compute the 3D transformation from a model coordinate frame into the sensor coordinate system. With perfect image data, these systems work well. With uncertain image data, however, their performance is less clear. We examine the effects of 2D sensor uncertainty on the computation of 3D model transformations. We use this analysis to bound the uncertainty in the transformation parameters, and the uncertainty associated with transforming other model features into the image. We also examine the impact of the such transformation uncertainty on recognition methods. |
| first_indexed | 2024-09-23T15:44:14Z |
| id | mit-1721.1/5959 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:44:14Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/59592019-04-10T16:35:22Z Recognizing 3D Ojbects of 2D Images: An Error Analysis Grimson, W. Eric Huttenlocher, Daniel P. Alter, T. D. object recognition error analysis Many object recognition systems use a small number of pairings of data and model features to compute the 3D transformation from a model coordinate frame into the sensor coordinate system. With perfect image data, these systems work well. With uncertain image data, however, their performance is less clear. We examine the effects of 2D sensor uncertainty on the computation of 3D model transformations. We use this analysis to bound the uncertainty in the transformation parameters, and the uncertainty associated with transforming other model features into the image. We also examine the impact of the such transformation uncertainty on recognition methods. 2004-10-04T14:24:10Z 2004-10-04T14:24:10Z 1992-07-01 AIM-1362 http://hdl.handle.net/1721.1/5959 en_US AIM-1362 32 p. 137449 bytes 547073 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | object recognition error analysis Grimson, W. Eric Huttenlocher, Daniel P. Alter, T. D. Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title | Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title_full | Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title_fullStr | Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title_full_unstemmed | Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title_short | Recognizing 3D Ojbects of 2D Images: An Error Analysis |
| title_sort | recognizing 3d ojbects of 2d images an error analysis |
| topic | object recognition error analysis |
| url | http://hdl.handle.net/1721.1/5959 |
| work_keys_str_mv | AT grimsonweric recognizing3dojbectsof2dimagesanerroranalysis AT huttenlocherdanielp recognizing3dojbectsof2dimagesanerroranalysis AT altertd recognizing3dojbectsof2dimagesanerroranalysis |