Mid-Level Vision and Recognition of Non-Rigid Objects
We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6792 |
| _version_ | 1811090297563643904 |
|---|---|
| author | Subirana-Vilanova, J. Brian |
| author_facet | Subirana-Vilanova, J. Brian |
| author_sort | Subirana-Vilanova, J. Brian |
| collection | MIT |
| description | We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/ incoming regions are more salient; and that perception begins by setting a reference frame (prior to early vision), and proceeds by processing convex structures. |
| first_indexed | 2024-09-23T14:41:38Z |
| id | mit-1721.1/6792 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:41:38Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/67922019-04-11T02:53:08Z Mid-Level Vision and Recognition of Non-Rigid Objects Subirana-Vilanova, J. Brian vision We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/ incoming regions are more salient; and that perception begins by setting a reference frame (prior to early vision), and proceeds by processing convex structures. 2004-10-20T19:55:13Z 2004-10-20T19:55:13Z 1995-04-01 AITR-1442 http://hdl.handle.net/1721.1/6792 en_US AITR-1442 239 p. 48192029 bytes 2356367 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | vision Subirana-Vilanova, J. Brian Mid-Level Vision and Recognition of Non-Rigid Objects |
| title | Mid-Level Vision and Recognition of Non-Rigid Objects |
| title_full | Mid-Level Vision and Recognition of Non-Rigid Objects |
| title_fullStr | Mid-Level Vision and Recognition of Non-Rigid Objects |
| title_full_unstemmed | Mid-Level Vision and Recognition of Non-Rigid Objects |
| title_short | Mid-Level Vision and Recognition of Non-Rigid Objects |
| title_sort | mid level vision and recognition of non rigid objects |
| topic | vision |
| url | http://hdl.handle.net/1721.1/6792 |
| work_keys_str_mv | AT subiranavilanovajbrian midlevelvisionandrecognitionofnonrigidobjects |