Three-Dimensional Object Registration Using Wavelet Features
Recent developments in shape-based modeling and data acquisition have brought three-dimensional models to the forefront of computer graphics and visualization research. New data acquisition methods are producing large numbers of models in a variety of fields. Three-dimensional registration (alignmen...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Springer London
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/49854 |
| _version_ | 1826214572957106176 |
|---|---|
| author | Chalfant, Julie Patrikalakis, Nicholas M. |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Chalfant, Julie Patrikalakis, Nicholas M. |
| author_sort | Chalfant, Julie |
| collection | MIT |
| description | Recent developments in shape-based modeling and data acquisition have brought three-dimensional models to the forefront of computer graphics and visualization research. New data acquisition methods are producing large numbers of models in a variety of fields. Three-dimensional registration (alignment) is key to the useful application of such models in areas from automated surface inspection to cancer detection and surgery. The algorithms developed in this research accomplish automatic registration of three-dimensional voxelized models. We employ features in a wavelet transform domain to accomplish registration. The features are extracted in a multi-resolutional format, thus delineating features at various scales for robust and rapid matching. Registration is achieved by using a voting scheme to select peaks in sets of rotation quaternions, then separately identifying translation. The method is robust to occlusion, clutter, and noise. The efficacy of the algorithm is demonstrated through examples from solid modeling and medical imaging applications. |
| first_indexed | 2024-09-23T16:07:35Z |
| format | Article |
| id | mit-1721.1/49854 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:07:35Z |
| publishDate | 2009 |
| publisher | Springer London |
| record_format | dspace |
| spelling | mit-1721.1/498542022-09-29T18:25:05Z Three-Dimensional Object Registration Using Wavelet Features Chalfant, Julie Patrikalakis, Nicholas M. Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Sea Grant College Program Patrikalakis, Nicholas M. Chalfant, Julie Patrikalakis, Nicholas M. wavelets shape-based matching 3D object registration Recent developments in shape-based modeling and data acquisition have brought three-dimensional models to the forefront of computer graphics and visualization research. New data acquisition methods are producing large numbers of models in a variety of fields. Three-dimensional registration (alignment) is key to the useful application of such models in areas from automated surface inspection to cancer detection and surgery. The algorithms developed in this research accomplish automatic registration of three-dimensional voxelized models. We employ features in a wavelet transform domain to accomplish registration. The features are extracted in a multi-resolutional format, thus delineating features at various scales for robust and rapid matching. Registration is achieved by using a voting scheme to select peaks in sets of rotation quaternions, then separately identifying translation. The method is robust to occlusion, clutter, and noise. The efficacy of the algorithm is demonstrated through examples from solid modeling and medical imaging applications. 2009-11-25T16:19:43Z 2009-11-25T16:19:43Z 2009-06 2008-05 Article http://purl.org/eprint/type/SubmittedJournalArticle 1435-5663 0177-0667 http://hdl.handle.net/1721.1/49854 Chalfant, Julie, and Nicholas Patrikalakis. “Three-dimensional object registration using wavelet features.” Engineering with Computers 25.3 (2009): 303-318. Web. en_US http://dx.doi.org/10.1007/s00366-009-0126-5 Engineering with Computers Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Springer London Nicholas M. Patrikalakis |
| spellingShingle | wavelets shape-based matching 3D object registration Chalfant, Julie Patrikalakis, Nicholas M. Three-Dimensional Object Registration Using Wavelet Features |
| title | Three-Dimensional Object Registration Using Wavelet Features |
| title_full | Three-Dimensional Object Registration Using Wavelet Features |
| title_fullStr | Three-Dimensional Object Registration Using Wavelet Features |
| title_full_unstemmed | Three-Dimensional Object Registration Using Wavelet Features |
| title_short | Three-Dimensional Object Registration Using Wavelet Features |
| title_sort | three dimensional object registration using wavelet features |
| topic | wavelets shape-based matching 3D object registration |
| url | http://hdl.handle.net/1721.1/49854 |
| work_keys_str_mv | AT chalfantjulie threedimensionalobjectregistrationusingwaveletfeatures AT patrikalakisnicholasm threedimensionalobjectregistrationusingwaveletfeatures |