Recognizing Rigid Objects by Aligning Them with an Image
This paper presents an approach to recognition where an object is first {\\it aligned} with an image using a small number of pairs of model and image features, and then the aligned model is compared directly against the image. To demonstrate the method, we present some examples of recognizing...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6456 |
| _version_ | 1811070778688405504 |
|---|---|
| author | Huttenlocher, Daniel P. Ullman, Shimon |
| author_facet | Huttenlocher, Daniel P. Ullman, Shimon |
| author_sort | Huttenlocher, Daniel P. |
| collection | MIT |
| description | This paper presents an approach to recognition where an object is first {\\it aligned} with an image using a small number of pairs of model and image features, and then the aligned model is compared directly against the image. To demonstrate the method, we present some examples of recognizing flat rigid objects with arbitrary three-dimensional position, orientation, and scale, from a single two-scale-space segmentation of edge contours. The method is extended to the domain of non-flat objects as well. |
| first_indexed | 2024-09-23T08:41:26Z |
| id | mit-1721.1/6456 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:41:26Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/64562019-04-09T19:13:34Z Recognizing Rigid Objects by Aligning Them with an Image Huttenlocher, Daniel P. Ullman, Shimon This paper presents an approach to recognition where an object is first {\\it aligned} with an image using a small number of pairs of model and image features, and then the aligned model is compared directly against the image. To demonstrate the method, we present some examples of recognizing flat rigid objects with arbitrary three-dimensional position, orientation, and scale, from a single two-scale-space segmentation of edge contours. The method is extended to the domain of non-flat objects as well. 2004-10-04T14:57:04Z 2004-10-04T14:57:04Z 1987-01-01 AIM-937 http://hdl.handle.net/1721.1/6456 en_US AIM-937 7384338 bytes 2839750 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Huttenlocher, Daniel P. Ullman, Shimon Recognizing Rigid Objects by Aligning Them with an Image |
| title | Recognizing Rigid Objects by Aligning Them with an Image |
| title_full | Recognizing Rigid Objects by Aligning Them with an Image |
| title_fullStr | Recognizing Rigid Objects by Aligning Them with an Image |
| title_full_unstemmed | Recognizing Rigid Objects by Aligning Them with an Image |
| title_short | Recognizing Rigid Objects by Aligning Them with an Image |
| title_sort | recognizing rigid objects by aligning them with an image |
| url | http://hdl.handle.net/1721.1/6456 |
| work_keys_str_mv | AT huttenlocherdanielp recognizingrigidobjectsbyaligningthemwithanimage AT ullmanshimon recognizingrigidobjectsbyaligningthemwithanimage |