{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/21486"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/21486","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Structure and motion estimation and recognition for curved three-dimensional objects","abstract":"The main focus of research in computer vision in the past has been on polyhedral objects that give rise to viewpoint-independent edges in the image. This thesis focuses on smooth curved objects that give rise to viewpoint-dependent edges. The research presented primarily focuses on the problems of structure and motion estimation and object recognition.","abstract_html":"The main focus of research in computer vision in the past has been on polyhedral objects that give rise to viewpoint-independent edges in the image. This thesis focuses on smooth curved objects that give rise to viewpoint-dependent edges. The research presented primarily focuses on the problems of structure and motion estimation and object recognition.","abstract_has_math":false,"creators":["Joshi, Tanuja Abhay"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Ahuja, Narendra"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-05-07T13:09:59Z","date_published":"2011-05-07T13:09:59Z","updated_at":"2026-07-22T22:25:18Z","subjects":["Engineering, Electronics and Electrical","Artificial Intelligence","Computer Science"],"languages":["eng"],"rights":["Copyright 1995 Joshi, Tanuja Abhay"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["AAI9624376","(UMI)AAI9624376"],"render_values":[{"text":"AAI9624376","href":null,"code":true},{"text":"(UMI)AAI9624376","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/21486","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ahuja, Narendra"]},{"key":"dc:creator","label":"Author","values":["Joshi, Tanuja Abhay"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-05-07T13:09:59Z","10000-01-01","1995"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering, Electronics and Electrical","Artificial Intelligence","Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 1995 Joshi, Tanuja Abhay"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["AAI9624376","(UMI)AAI9624376","http://hdl.handle.net/2142/21486"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The main focus of research in computer vision in the past has been on polyhedral objects that give rise to viewpoint-independent edges in the image. This thesis focuses on smooth curved objects that give rise to viewpoint-dependent edges. The research presented primarily focuses on the problems of structure and motion estimation and object recognition.","In the first part of the thesis, the structure and motion of a smooth object are estimated from its silhouettes observed by a trinocular stereo rig over time. First, a model is constructed for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive frames. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) that are used to bootstrap the motion estimation process. Points on the entire silhouette, along with the reconstructed local structures, are then used to refine the initial motion estimate. The proposed approach is implemented and results obtained on real images are presented.","The second part of the thesis presents a new algorithm for recognition of curved 3D objects from 2D images. The algorithm is based on a representation composed of a discrete set of HOT curves at which the surface admits High Order Tangents. A method is presented to automatically construct two of the HOT curves (the parabolic and limiting bitangent curves) using the results of the above structure and motion estimation algorithm. There is a natural correspondence between these two HOT curves and certain silhouette features: the inflections and the bitangents. The recognition approach uses these silhouette features to compute a set of scale-independent image observables that serve as indices in a database of models. This database is used for pose estimation and model identification. Hypotheses formed through indexing are verified through pose estimation. The results obtained on real images are presented.","Made available in DSpace on 2011-05-07T13:09:59Z (GMT). No. of bitstreams: 2 license.txt: 4922 bytes, checksum: 910b249b4beec47e7ab768910c8f966f (MD5) 9624376.pdf: 5678180 bytes, checksum: 9bd69dd682b8d75a703216bed0918637 (MD5) Previous issue date: 1995","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Howard Ding (hding2@illinois.edu) on 2011-05-07T14:51:07Z Item is restricted indefinitely.","Restriction data tranferred 2014-07-01T11:23:25-05:00 Original Data Group with Access UIUC Users [automated] Release Date: none Reason: ETDs are only available to UIUC Users without author permission","ETDs are only available to UIUC Users without author permission","U of I Only"]},{"key":"dc:title","label":"Title","values":["Structure and motion estimation and recognition for curved three-dimensional objects"]}]}],"canonical_facts":{"dc:contributor":["Ahuja, Narendra"],"dc:creator":["Joshi, Tanuja Abhay"],"dc:date":["2011-05-07T13:09:59Z","10000-01-01","1995"],"dc:description":["The main focus of research in computer vision in the past has been on polyhedral objects that give rise to viewpoint-independent edges in the image. This thesis focuses on smooth curved objects that give rise to viewpoint-dependent edges. The research presented primarily focuses on the problems of structure and motion estimation and object recognition.","In the first part of the thesis, the structure and motion of a smooth object are estimated from its silhouettes observed by a trinocular stereo rig over time. First, a model is constructed for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive frames. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) that are used to bootstrap the motion estimation process. Points on the entire silhouette, along with the reconstructed local structures, are then used to refine the initial motion estimate. The proposed approach is implemented and results obtained on real images are presented.","The second part of the thesis presents a new algorithm for recognition of curved 3D objects from 2D images. The algorithm is based on a representation composed of a discrete set of HOT curves at which the surface admits High Order Tangents. A method is presented to automatically construct two of the HOT curves (the parabolic and limiting bitangent curves) using the results of the above structure and motion estimation algorithm. There is a natural correspondence between these two HOT curves and certain silhouette features: the inflections and the bitangents. The recognition approach uses these silhouette features to compute a set of scale-independent image observables that serve as indices in a database of models. This database is used for pose estimation and model identification. Hypotheses formed through indexing are verified through pose estimation. The results obtained on real images are presented.","Made available in DSpace on 2011-05-07T13:09:59Z (GMT). No. of bitstreams: 2 license.txt: 4922 bytes, checksum: 910b249b4beec47e7ab768910c8f966f (MD5) 9624376.pdf: 5678180 bytes, checksum: 9bd69dd682b8d75a703216bed0918637 (MD5) Previous issue date: 1995","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by Howard Ding (hding2@illinois.edu) on 2011-05-07T14:51:07Z Item is restricted indefinitely.","Restriction data tranferred 2014-07-01T11:23:25-05:00 Original Data Group with Access UIUC Users [automated] Release Date: none Reason: ETDs are only available to UIUC Users without author permission","ETDs are only available to UIUC Users without author permission","U of I Only"],"dc:identifier":["AAI9624376","(UMI)AAI9624376","http://hdl.handle.net/2142/21486"],"dc:language":["eng"],"dc:rights":["Copyright 1995 Joshi, Tanuja Abhay"],"dc:subject":["Engineering, Electronics and Electrical","Artificial Intelligence","Computer Science"],"dc:title":["Structure and motion estimation and recognition for curved three-dimensional objects"],"dc:type":["text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:18Z"}