{"id":{"repo_id":"birmingham","oai_identifier":"oai:etheses.bham.ac.uk:15459"},"canonical_url":"https://search.ndltd.org/etd/birmingham/oai:etheses.bham.ac.uk:15459","repository":{"repo_id":"birmingham","name":"University of Birmingham","base_url":"https://etheses.bham.ac.uk/cgi/oai2"},"display":{"title":"Visual 6D object pose estimation and tracking","abstract":"Visual 6D object pose estimation and tracking is crucial for enabling machines to understand and interact with the three-dimensional world. Despite significant advancements, challenges persist in this field. Existing methods often struggle in complex real-world scenarios, particularly with symmetric and textureless objects under occlusion. Category-level methods also face limitations in generalizability, especially with complex-shaped objects and noisy environments. Additionally, there is a significant gap in effective methods for category-level object pose refinement, which is crucial for achieving high-precision pose information with previously unseen objects. To address these challenges, this thesis proposes three approaches. First, an instance-level object pose tracking method is introduced, leveraging temporal information with augmented autoencoder-based reconstruction to enhance robustness to symmetric and textureless objects under occlusion. Second, a hybrid scope feature extraction layer (HS-layer) is presented for category-level object pose estimation. The HS layer encodes translation and scale information, perceives geometric structural information for handling complex-shaped objects with robustness to outliers. Lastly, a method that combines latent geometric feature extraction and learnable affine transformation is proposed to address shape discrepancy issues in category-level object pose refinement, improving pose refinement accuracy and generalizability. Extensive experiments validate the effectiveness of these approaches in advancing practical applications of visual 6D object pose estimation and tracking. Additionally, all the proposed methods exhibit real-time performance, crucial for real-life applications.","abstract_html":"Visual 6D object pose estimation and tracking is crucial for enabling machines to understand and interact with the three-dimensional world. Despite significant advancements, challenges persist in this field. Existing methods often struggle in complex real-world scenarios, particularly with symmetric and textureless objects under occlusion. Category-level methods also face limitations in generalizability, especially with complex-shaped objects and noisy environments. Additionally, there is a significant gap in effective methods for category-level object pose refinement, which is crucial for achieving high-precision pose information with previously unseen objects. To address these challenges, this thesis proposes three approaches. First, an instance-level object pose tracking method is introduced, leveraging temporal information with augmented autoencoder-based reconstruction to enhance robustness to symmetric and textureless objects under occlusion. Second, a hybrid scope feature extraction layer (HS-layer) is presented for category-level object pose estimation. The HS layer encodes translation and scale information, perceives geometric structural information for handling complex-shaped objects with robustness to outliers. Lastly, a method that combines latent geometric feature extraction and learnable affine transformation is proposed to address shape discrepancy issues in category-level object pose refinement, improving pose refinement accuracy and generalizability. Extensive experiments validate the effectiveness of these approaches in advancing practical applications of visual 6D object pose estimation and tracking. Additionally, all the proposed methods exhibit real-time performance, crucial for real-life applications.","abstract_has_math":false,"creators":["Zheng, Linfang"],"institution":"University of Birmingham","degree_name":"d_ph","degree_level":"d_ph","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-12","date_published":"2024-12","updated_at":"2026-11-19T09:32:56Z","subjects":["T Technology (General)"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["Shenzhen Science and Technology Program under Grant JCYJ20200109141601708","Science, Technology and Innovation Commission of Shenzhen Municipality under grant ZDSYS20200811143601004","Benchmarks for UndeRstanding Grasping (BURG) (EP/S032487/1)","ITRC (Information Technology Research Center) support program (IITP-2024-2020-0-01789)","the Institute of Information and communications Technology Planning and evaluation (IITP) grant funded by the Korea government (MSIT) (2021-0-00537, Visual common sense through self-supervised learning for restoration of invisible parts in images)","the Shenzhen Key Laboratory of Control Theory and Intelligent Systems, under grant No.ZDSYS20220330161800001"],"render_values":[{"text":"Shenzhen Science and Technology Program under Grant JCYJ20200109141601708","href":null,"code":true},{"text":"Science, Technology and Innovation Commission of Shenzhen Municipality under grant ZDSYS20200811143601004","href":null,"code":true},{"text":"Benchmarks for UndeRstanding Grasping (BURG) (EP/S032487/1)","href":null,"code":true},{"text":"ITRC (Information Technology Research Center) support program (IITP-2024-2020-0-01789)","href":null,"code":true},{"text":"the Institute of Information and communications Technology Planning and evaluation (IITP) grant funded by the Korea government (MSIT) (2021-0-00537, Visual common sense through self-supervised learning for restoration of invisible parts in images)","href":null,"code":true},{"text":"the Shenzhen Key Laboratory of Control Theory and Intelligent Systems, under grant No.ZDSYS20220330161800001","href":null,"code":true}]}],"person_identifier_entries":[{"key":"person:identifier.orcid","label":"ORCID","values":["0009000180068325"],"render_values":[{"text":"0009-0001-8006-8325","href":"https://orcid.org/0009-0001-8006-8325","code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"http://etheses.bham.ac.uk//id/eprint/15459/7/Zheng2024PhD.pdf","download_label":"Download PDF","download_source":"dc:identifier.uri","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://etheses.bham.ac.uk/cgi/oai2?verb=GetRecord&metadataPrefix=uketd_dc&identifier=oai%3Aetheses.bham.ac.uk%3A15459","prefix":"uketd_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["other"]},{"key":"dc:creator","label":"Author","values":["Zheng, Linfang"]},{"key":"person:identifier.orcid","label":"ORCID","values":["0009000180068325"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-12-10"]},{"key":"dc:date.issued","label":"Date","values":["2024-12"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["College of Engineering & Physical Sciences","School of Computer Science"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Birmingham"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://etheses.bham.ac.uk//id/eprint/15459/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["d_ph"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["d_ph"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["T Technology (General)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.dcterms_iso639_2","label":"Language (ISO 639-2)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["Shenzhen Science and Technology Program under Grant JCYJ20200109141601708","Science, Technology and Innovation Commission of Shenzhen Municipality under grant ZDSYS20200811143601004","Benchmarks for UndeRstanding Grasping (BURG) (EP/S032487/1)","ITRC (Information Technology Research Center) support program (IITP-2024-2020-0-01789)","the Institute of Information and communications Technology Planning and evaluation (IITP) grant funded by the Korea government (MSIT) (2021-0-00537, Visual common sense through self-supervised learning for restoration of invisible parts in images)","the Shenzhen Key Laboratory of Control Theory and Intelligent Systems, under grant No.ZDSYS20220330161800001"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://etheses.bham.ac.uk//id/eprint/15459/7/Zheng2024PhD.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Visual 6D object pose estimation and tracking is crucial for enabling machines to understand and interact with the three-dimensional world. Despite significant advancements, challenges persist in this field. Existing methods often struggle in complex real-world scenarios, particularly with symmetric and textureless objects under occlusion. Category-level methods also face limitations in generalizability, especially with complex-shaped objects and noisy environments. Additionally, there is a significant gap in effective methods for category-level object pose refinement, which is crucial for achieving high-precision pose information with previously unseen objects. To address these challenges, this thesis proposes three approaches. First, an instance-level object pose tracking method is introduced, leveraging temporal information with augmented autoencoder-based reconstruction to enhance robustness to symmetric and textureless objects under occlusion. Second, a hybrid scope feature extraction layer (HS-layer) is presented for category-level object pose estimation. The HS layer encodes translation and scale information, perceives geometric structural information for handling complex-shaped objects with robustness to outliers. Lastly, a method that combines latent geometric feature extraction and learnable affine transformation is proposed to address shape discrepancy issues in category-level object pose refinement, improving pose refinement accuracy and generalizability. Extensive experiments validate the effectiveness of these approaches in advancing practical applications of visual 6D object pose estimation and tracking. Additionally, all the proposed methods exhibit real-time performance, crucial for real-life applications."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dcterms:accessrights","label":"Dcterms Accessrights","values":["public"]},{"key":"dc:title","label":"Title","values":["Visual 6D object pose estimation and tracking"]}]}],"canonical_facts":{"dc:contributor.sponsor":["other"],"dc:creator":["Zheng, Linfang"],"dc:date":["2024-12-10"],"dc:date.issued":["2024-12"],"dc:description.abstract":["Visual 6D object pose estimation and tracking is crucial for enabling machines to understand and interact with the three-dimensional world. Despite significant advancements, challenges persist in this field. Existing methods often struggle in complex real-world scenarios, particularly with symmetric and textureless objects under occlusion. Category-level methods also face limitations in generalizability, especially with complex-shaped objects and noisy environments. Additionally, there is a significant gap in effective methods for category-level object pose refinement, which is crucial for achieving high-precision pose information with previously unseen objects. To address these challenges, this thesis proposes three approaches. First, an instance-level object pose tracking method is introduced, leveraging temporal information with augmented autoencoder-based reconstruction to enhance robustness to symmetric and textureless objects under occlusion. Second, a hybrid scope feature extraction layer (HS-layer) is presented for category-level object pose estimation. The HS layer encodes translation and scale information, perceives geometric structural information for handling complex-shaped objects with robustness to outliers. Lastly, a method that combines latent geometric feature extraction and learnable affine transformation is proposed to address shape discrepancy issues in category-level object pose refinement, improving pose refinement accuracy and generalizability. Extensive experiments validate the effectiveness of these approaches in advancing practical applications of visual 6D object pose estimation and tracking. Additionally, all the proposed methods exhibit real-time performance, crucial for real-life applications."],"dc:format":["text"],"dc:identifier.grantnumber":["Shenzhen Science and Technology Program under Grant JCYJ20200109141601708","Science, Technology and Innovation Commission of Shenzhen Municipality under grant ZDSYS20200811143601004","Benchmarks for UndeRstanding Grasping (BURG) (EP/S032487/1)","ITRC (Information Technology Research Center) support program (IITP-2024-2020-0-01789)","the Institute of Information and communications Technology Planning and evaluation (IITP) grant funded by the Korea government (MSIT) (2021-0-00537, Visual common sense through self-supervised learning for restoration of invisible parts in images)","the Shenzhen Key Laboratory of Control Theory and Intelligent Systems, under grant No.ZDSYS20220330161800001"],"dc:identifier.uri":["http://etheses.bham.ac.uk//id/eprint/15459/7/Zheng2024PhD.pdf"],"dc:language.dcterms_iso639_2":["eng"],"dc:publisher.department":["College of Engineering & Physical Sciences","School of Computer Science"],"dc:publisher.institution":["University of Birmingham"],"dc:relation.isreferencedby":["http://etheses.bham.ac.uk//id/eprint/15459/"],"dc:subject":["T Technology (General)"],"dcterms:accessrights":["public"],"dc:title":["Visual 6D object pose estimation and tracking"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["d_ph"],"dc:type.qualificationname":["d_ph"],"person:identifier.orcid":["0009000180068325"]},"updated_at":"2026-11-19T09:32:56Z"}