Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images
In model-based vision, there are a huge number of possible ways to match model features to image features. In addition to model shape constraints, there are important match-independent constraints that can efficiently reduce the search without the combinatorics of matching. I demonstrate two...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7039 |
| _version_ | 1811096034480226304 |
|---|---|
| author | Clemens, David T. |
| author_facet | Clemens, David T. |
| author_sort | Clemens, David T. |
| collection | MIT |
| description | In model-based vision, there are a huge number of possible ways to match model features to image features. In addition to model shape constraints, there are important match-independent constraints that can efficiently reduce the search without the combinatorics of matching. I demonstrate two specific modules in the context of a complete recognition system, Reggie. The first is a region-based grouping mechanism to find groups of image features that are likely to come from a single object. The second is an interpretive matching scheme to make explicit hypotheses about occlusion and instabilities in the image features. |
| first_indexed | 2024-09-23T16:37:17Z |
| id | mit-1721.1/7039 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:37:17Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/70392019-04-10T11:52:23Z Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images Clemens, David T. In model-based vision, there are a huge number of possible ways to match model features to image features. In addition to model shape constraints, there are important match-independent constraints that can efficiently reduce the search without the combinatorics of matching. I demonstrate two specific modules in the context of a complete recognition system, Reggie. The first is a region-based grouping mechanism to find groups of image features that are likely to come from a single object. The second is an interpretive matching scheme to make explicit hypotheses about occlusion and instabilities in the image features. 2004-10-20T20:23:24Z 2004-10-20T20:23:24Z 1991-06-01 AITR-1307 http://hdl.handle.net/1721.1/7039 en_US AITR-1307 22413823 bytes 8247283 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Clemens, David T. Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title | Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title_full | Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title_fullStr | Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title_full_unstemmed | Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title_short | Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images |
| title_sort | region based feature interpretation for recognizing 3d models in 2d images |
| url | http://hdl.handle.net/1721.1/7039 |
| work_keys_str_mv | AT clemensdavidt regionbasedfeatureinterpretationforrecognizing3dmodelsin2dimages |