Recognizing 3-D Objects Using 2-D Images
We discuss a strategy for visual recognition by forming groups of salient image features, and then using these groups to index into a data base to find all of the matching groups of model features. We discuss the most space efficient possible method of representing 3-D models for indexing from...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6796 |
| _version_ | 1826190787698753536 |
|---|---|
| author | Jacobs, David W. |
| author_facet | Jacobs, David W. |
| author_sort | Jacobs, David W. |
| collection | MIT |
| description | We discuss a strategy for visual recognition by forming groups of salient image features, and then using these groups to index into a data base to find all of the matching groups of model features. We discuss the most space efficient possible method of representing 3-D models for indexing from 2-D data, and show how to account for sensing error when indexing. We also present a convex grouping method that is robust and efficient, both theoretically and in practice. Finally, we combine these modules into a complete recognition system, and test its performance on many real images. |
| first_indexed | 2024-09-23T08:45:40Z |
| id | mit-1721.1/6796 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:45:40Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/67962019-04-10T07:21:00Z Recognizing 3-D Objects Using 2-D Images Jacobs, David W. grouping indexing recognition invariants sensing erro snon-accidental properties We discuss a strategy for visual recognition by forming groups of salient image features, and then using these groups to index into a data base to find all of the matching groups of model features. We discuss the most space efficient possible method of representing 3-D models for indexing from 2-D data, and show how to account for sensing error when indexing. We also present a convex grouping method that is robust and efficient, both theoretically and in practice. Finally, we combine these modules into a complete recognition system, and test its performance on many real images. 2004-10-20T19:55:20Z 2004-10-20T19:55:20Z 1993-04-01 AITR-1416 http://hdl.handle.net/1721.1/6796 en_US AITR-1416 269 p. 3519825 bytes 7005877 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | grouping indexing recognition invariants sensing erro snon-accidental properties Jacobs, David W. Recognizing 3-D Objects Using 2-D Images |
| title | Recognizing 3-D Objects Using 2-D Images |
| title_full | Recognizing 3-D Objects Using 2-D Images |
| title_fullStr | Recognizing 3-D Objects Using 2-D Images |
| title_full_unstemmed | Recognizing 3-D Objects Using 2-D Images |
| title_short | Recognizing 3-D Objects Using 2-D Images |
| title_sort | recognizing 3 d objects using 2 d images |
| topic | grouping indexing recognition invariants sensing erro snon-accidental properties |
| url | http://hdl.handle.net/1721.1/6796 |
| work_keys_str_mv | AT jacobsdavidw recognizing3dobjectsusing2dimages |