The Alignment of Objects with Smooth Surfaces
This paper examines the recognition of rigid objects bounded by smooth surfaces using an alignment approach. The projected image of such an object changes during rotation in a manner that is difficult to predict. A method to approach this problem is suggested, using the 3D surface curvature at...
Main Authors: | , |
---|---|
Language: | en_US |
Published: |
2004
|
Online Access: | http://hdl.handle.net/1721.1/6492 |
_version_ | 1826208990461165568 |
---|---|
author | Ullman, Shimon Basri, Ronen |
author_facet | Ullman, Shimon Basri, Ronen |
author_sort | Ullman, Shimon |
collection | MIT |
description | This paper examines the recognition of rigid objects bounded by smooth surfaces using an alignment approach. The projected image of such an object changes during rotation in a manner that is difficult to predict. A method to approach this problem is suggested, using the 3D surface curvature at the points along the silhouette. The curvature information requires a single number for each point along the object's silhouette, the magnitude of the curvature vector at the point. We have implemented and tested this method on images of complex 3D objects; it was found to give accurate predictions of the objects' appearances for large transformations. A small number of models can be used to predict the new appearance of an object from any viewpoint. |
first_indexed | 2024-09-23T14:15:56Z |
id | mit-1721.1/6492 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T14:15:56Z |
publishDate | 2004 |
record_format | dspace |
spelling | mit-1721.1/64922019-04-10T18:33:52Z The Alignment of Objects with Smooth Surfaces Ullman, Shimon Basri, Ronen This paper examines the recognition of rigid objects bounded by smooth surfaces using an alignment approach. The projected image of such an object changes during rotation in a manner that is difficult to predict. A method to approach this problem is suggested, using the 3D surface curvature at the points along the silhouette. The curvature information requires a single number for each point along the object's silhouette, the magnitude of the curvature vector at the point. We have implemented and tested this method on images of complex 3D objects; it was found to give accurate predictions of the objects' appearances for large transformations. A small number of models can be used to predict the new appearance of an object from any viewpoint. 2004-10-04T15:12:54Z 2004-10-04T15:12:54Z 1988-07-01 AIM-1060 http://hdl.handle.net/1721.1/6492 en_US AIM-1060 2548385 bytes 987531 bytes application/postscript application/pdf application/postscript application/pdf |
spellingShingle | Ullman, Shimon Basri, Ronen The Alignment of Objects with Smooth Surfaces |
title | The Alignment of Objects with Smooth Surfaces |
title_full | The Alignment of Objects with Smooth Surfaces |
title_fullStr | The Alignment of Objects with Smooth Surfaces |
title_full_unstemmed | The Alignment of Objects with Smooth Surfaces |
title_short | The Alignment of Objects with Smooth Surfaces |
title_sort | alignment of objects with smooth surfaces |
url | http://hdl.handle.net/1721.1/6492 |
work_keys_str_mv | AT ullmanshimon thealignmentofobjectswithsmoothsurfaces AT basrironen thealignmentofobjectswithsmoothsurfaces AT ullmanshimon alignmentofobjectswithsmoothsurfaces AT basrironen alignmentofobjectswithsmoothsurfaces |