{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/469"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/469","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"A framework for video-driven crowd synthesis.","abstract":"We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exemplar crowd videos. Motion vectors collected over the duration of the video are processed to compute global motion paths. These paths encode the dominant motions observed during the course of the video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the \\visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under di fferent settings and the initial results appear promising.","abstract_html":"We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exemplar crowd videos. Motion vectors collected over the duration of the video are processed to compute global motion paths. These paths encode the dominant motions observed during the course of the video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the \\visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under di fferent settings and the initial results appear promising.","abstract_has_math":false,"creators":["Stadler, Jordan J."],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Nuclear Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Qureshi, Faisal Z."],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-09-01","date_published":"2014-09-01","updated_at":"2026-07-24T05:35:16Z","subjects":["Framework","Data-driven","Crowd analysis","Crowd synthesis"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/469","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Qureshi, Faisal Z."]},{"key":"dc:creator","label":"Author","values":["Stadler, Jordan J."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-10-27T16:09:04Z","2022-03-30T17:05:48Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-10-27T16:09:04Z","2022-03-30T17:05:48Z"]},{"key":"dc:date.issued","label":"Date","values":["2014-09-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Nuclear Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Framework","Data-driven","Crowd analysis","Crowd synthesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/469"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exemplar crowd videos. Motion vectors collected over the duration of the video are processed to compute global motion paths. These paths encode the dominant motions observed during the course of the video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the \\visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under di fferent settings and the initial results appear promising."]},{"key":"dc:title","label":"Title","values":["A framework for video-driven crowd synthesis."]}]}],"canonical_facts":{"dc:contributor.advisor":["Qureshi, Faisal Z."],"dc:creator":["Stadler, Jordan J."],"dc:date.accessioned":["2014-10-27T16:09:04Z","2022-03-30T17:05:48Z"],"dc:date.available":["2014-10-27T16:09:04Z","2022-03-30T17:05:48Z"],"dc:date.issued":["2014-09-01"],"dc:description.abstract":["We present a framework for video-driven crowd synthesis. The proposed framework employs motion analysis techniques to extract inter-frame motion vectors from the exemplar crowd videos. Motion vectors collected over the duration of the video are processed to compute global motion paths. These paths encode the dominant motions observed during the course of the video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the \\visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under di fferent settings and the initial results appear promising."],"dc:identifier.uri":["https://hdl.handle.net/10155/469"],"dc:language.iso":["en"],"dc:subject":["Framework","Data-driven","Crowd analysis","Crowd synthesis"],"dc:title":["A framework for video-driven crowd synthesis."],"dc:type":["Thesis"],"thesis:degree_discipline":["Nuclear Engineering"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:16Z"}