The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method

The recognition of objects with smooth bounding surfaces from their contour images is considerably more complicated than that of objects with sharp edges, since in the former case the set of object points that generates the silhouette contours changes from one view to another. The "curvature me...

Full description

Bibliographic Details
Main Author: Basri, Ronen
Language:en_US
Published: 2004
Online Access:http://hdl.handle.net/1721.1/6582
_version_ 1811083276015632384
author Basri, Ronen
author_facet Basri, Ronen
author_sort Basri, Ronen
collection MIT
description The recognition of objects with smooth bounding surfaces from their contour images is considerably more complicated than that of objects with sharp edges, since in the former case the set of object points that generates the silhouette contours changes from one view to another. The "curvature method", developed by Basri and Ullman [1988], provides a method to approximate the appearance of such objects from different viewpoints. In this paper we analyze the curvature method. We apply the method to ellipsoidal objects and compute analytically the error obtained for different rotations of the objects. The error depends on the exact shape of the ellipsoid (namely, the relative lengths of its axes), and it increases a sthe ellipsoid becomes "deep" (elongated in the Z-direction). We show that the errors are usually small, and that, in general, a small number of models is required to predict the appearance of an ellipsoid from all possible views. Finally, we show experimentally that the curvature method applies as well to objects with hyperbolic surface patches.
first_indexed 2024-09-23T12:30:29Z
id mit-1721.1/6582
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T12:30:29Z
publishDate 2004
record_format dspace
spelling mit-1721.1/65822019-04-11T02:52:32Z The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method Basri, Ronen The recognition of objects with smooth bounding surfaces from their contour images is considerably more complicated than that of objects with sharp edges, since in the former case the set of object points that generates the silhouette contours changes from one view to another. The "curvature method", developed by Basri and Ullman [1988], provides a method to approximate the appearance of such objects from different viewpoints. In this paper we analyze the curvature method. We apply the method to ellipsoidal objects and compute analytically the error obtained for different rotations of the objects. The error depends on the exact shape of the ellipsoid (namely, the relative lengths of its axes), and it increases a sthe ellipsoid becomes "deep" (elongated in the Z-direction). We show that the errors are usually small, and that, in general, a small number of models is required to predict the appearance of an ellipsoid from all possible views. Finally, we show experimentally that the curvature method applies as well to objects with hyperbolic surface patches. 2004-10-08T20:28:59Z 2004-10-08T20:28:59Z 1991-11-01 AIM-1332 http://hdl.handle.net/1721.1/6582 en_US AIM-1332 1331689 bytes 1036207 bytes application/postscript application/pdf application/postscript application/pdf
spellingShingle Basri, Ronen
The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title_full The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title_fullStr The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title_full_unstemmed The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title_short The Alignment of Objects With Smooth Surfaces: Error Analysis of the Curvature Method
title_sort alignment of objects with smooth surfaces error analysis of the curvature method
url http://hdl.handle.net/1721.1/6582
work_keys_str_mv AT basrironen thealignmentofobjectswithsmoothsurfaceserroranalysisofthecurvaturemethod
AT basrironen alignmentofobjectswithsmoothsurfaceserroranalysisofthecurvaturemethod