{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/45222"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/45222","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Learned structural and temporal context for dynamic 3D pose optimization and tracking","abstract":"Accurate 3D tracking of animals from video recordings is critical for many behavioral studies. However, other than for humans, there is a lack of publicly available datasets of videos of animals that the computer vision community could use for model development. Furthermore, due to occlusion and the uncontrollable nature of the animals, existing pose estimation models suffer from inadequate precision. People rely on biomechanical expertise to design mathematical models to optimize poses to mitigate this issue at the cost of generalization. We propose OptiPose, a generalizable attention-based deep learning pose optimization model, as a part of a post-processing pipeline for refining 3D poses estimated by pre-existing systems. Our experiments show how OptiPose is highly robust to noise and occlusion and can be used to optimize pose sequences provided by state-of-the-art models for animal pose estimation. Furthermore, we will make Rodent3D, a multimodal (RGB, Thermal, and Depth) dataset for rats, publicly available.","abstract_html":"Accurate 3D tracking of animals from video recordings is critical for many behavioral studies. However, other than for humans, there is a lack of publicly available datasets of videos of animals that the computer vision community could use for model development. Furthermore, due to occlusion and the uncontrollable nature of the animals, existing pose estimation models suffer from inadequate precision. People rely on biomechanical expertise to design mathematical models to optimize poses to mitigate this issue at the cost of generalization. We propose OptiPose, a generalizable attention-based deep learning pose optimization model, as a part of a post-processing pipeline for refining 3D poses estimated by pre-existing systems. Our experiments show how OptiPose is highly robust to noise and occlusion and can be used to optimize pose sequences provided by state-of-the-art models for animal pose estimation. Furthermore, we will make Rodent3D, a multimodal (RGB, Thermal, and Depth) dataset for rats, publicly available.","abstract_has_math":false,"creators":["Patel, Mahir"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Betke, Margrit"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022","date_published":"2022","updated_at":"2026-11-18T19:44:51Z","subjects":["Artificial intelligence","Computer vision","Deep learning","Pose estimation","Pose optimization","Pose tracking"],"languages":["en_US"],"rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2144/45222","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/45222","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F45222","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Betke, Margrit"]},{"key":"dc:creator","label":"Author","values":["Patel, Mahir"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-10-03T18:40:13Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-10-03T18:40:13Z"]},{"key":"dc:date.issued","label":"Date","values":["2022"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2022-09-30T01:03:51Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence","Computer vision","Deep learning","Pose estimation","Pose optimization","Pose tracking"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-ShareAlike 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by-nc-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/45222"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Accurate 3D tracking of animals from video recordings is critical for many behavioral studies. However, other than for humans, there is a lack of publicly available datasets of videos of animals that the computer vision community could use for model development. Furthermore, due to occlusion and the uncontrollable nature of the animals, existing pose estimation models suffer from inadequate precision. People rely on biomechanical expertise to design mathematical models to optimize poses to mitigate this issue at the cost of generalization. We propose OptiPose, a generalizable attention-based deep learning pose optimization model, as a part of a post-processing pipeline for refining 3D poses estimated by pre-existing systems. Our experiments show how OptiPose is highly robust to noise and occlusion and can be used to optimize pose sequences provided by state-of-the-art models for animal pose estimation. Furthermore, we will make Rodent3D, a multimodal (RGB, Thermal, and Depth) dataset for rats, publicly available."]},{"key":"dc:title","label":"Title","values":["Learned structural and temporal context for dynamic 3D pose optimization and tracking"]}]}],"canonical_facts":{"dc:contributor.advisor":["Betke, Margrit"],"dc:creator":["Patel, Mahir"],"dc:date.accessioned":["2022-10-03T18:40:13Z"],"dc:date.available":["2022-10-03T18:40:13Z"],"dc:date.issued":["2022"],"dc:date.updated":["2022-09-30T01:03:51Z"],"dc:description.abstract":["Accurate 3D tracking of animals from video recordings is critical for many behavioral studies. However, other than for humans, there is a lack of publicly available datasets of videos of animals that the computer vision community could use for model development. Furthermore, due to occlusion and the uncontrollable nature of the animals, existing pose estimation models suffer from inadequate precision. People rely on biomechanical expertise to design mathematical models to optimize poses to mitigate this issue at the cost of generalization. We propose OptiPose, a generalizable attention-based deep learning pose optimization model, as a part of a post-processing pipeline for refining 3D poses estimated by pre-existing systems. Our experiments show how OptiPose is highly robust to noise and occlusion and can be used to optimize pose sequences provided by state-of-the-art models for animal pose estimation. Furthermore, we will make Rodent3D, a multimodal (RGB, Thermal, and Depth) dataset for rats, publicly available."],"dc:identifier.uri":["https://hdl.handle.net/2144/45222"],"dc:language.iso":["en_US"],"dc:rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by-nc-sa/4.0/"],"dc:subject":["Artificial intelligence","Computer vision","Deep learning","Pose estimation","Pose optimization","Pose tracking"],"dc:title":["Learned structural and temporal context for dynamic 3D pose optimization and tracking"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T19:44:51Z"}