{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-1643"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-1643","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Non-rigid multi-modal object tracking using Gaussian mixture models","abstract":"This work presents an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragment set and its cardinality are automatically adapted to the image data using an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. The fragment modeling is used to generate a strength map indicating the probability of each pixel belonging to the foreground. The strength map provides vital information about new fragments appearing in the scene, thereby assisting in addressing problematic cases like self-occlusion. The strength map is used by the region growing formulation, reminiscent of discrete level set implementation, to extract accurate boundaries of the target. Significant speedup is achieved using the region growing procedure over traditional level set based methods. The joint Lucas-Kanade feature tracking approach is also incorporated for handling large unpredictable motions even in untextured regions. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique.","abstract_html":"This work presents an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragment set and its cardinality are automatically adapted to the image data using an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. The fragment modeling is used to generate a strength map indicating the probability of each pixel belonging to the foreground. The strength map provides vital information about new fragments appearing in the scene, thereby assisting in addressing problematic cases like self-occlusion. The strength map is used by the region growing formulation, reminiscent of discrete level set implementation, to extract accurate boundaries of the target. Significant speedup is achieved using the region growing procedure over traditional level set based methods. The joint Lucas-Kanade feature tracking approach is also incorporated for handling large unpredictable motions even in untextured regions. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique.","abstract_has_math":false,"creators":["Chockalingam, Prakash"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Engineering","degree_department":null,"school":null,"contributors":["Birchfield, Stan","Schalkoff , Robert","Dean , Brian"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:07:16Z","subjects":["Fragment","Gaussian mixture models","level sets","Multi-Modal","Strength image","Tracking","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/643","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/643","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-1643","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Birchfield, Stan","Schalkoff , Robert","Dean , Brian"]},{"key":"dc:creator","label":"Author","values":["Chockalingam, Prakash"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2015-09-30T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2009-08-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Fragment","Gaussian mixture models","level sets","Multi-Modal","Strength image","Tracking","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/643"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This work presents an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragment set and its cardinality are automatically adapted to the image data using an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. The fragment modeling is used to generate a strength map indicating the probability of each pixel belonging to the foreground. The strength map provides vital information about new fragments appearing in the scene, thereby assisting in addressing problematic cases like self-occlusion. The strength map is used by the region growing formulation, reminiscent of discrete level set implementation, to extract accurate boundaries of the target. Significant speedup is achieved using the region growing procedure over traditional level set based methods. The joint Lucas-Kanade feature tracking approach is also incorporated for handling large unpredictable motions even in untextured regions. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique."]},{"key":"dc:title","label":"Title","values":["Non-rigid multi-modal object tracking using Gaussian mixture models"]}]}],"canonical_facts":{"dc:contributor":["Birchfield, Stan","Schalkoff , Robert","Dean , Brian"],"dc:creator":["Chockalingam, Prakash"],"dc:date.available":["2015-09-30T07:00:00Z"],"dc:date.created":["2009-08-01T07:00:00Z"],"dc:description.abstract":["This work presents an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature-spatial space, with each ellipsoid corresponding to a different fragment. The fragment set and its cardinality are automatically adapted to the image data using an efficient region-growing procedure and updated according to a weighted average of the past and present image statistics. The fragment modeling is used to generate a strength map indicating the probability of each pixel belonging to the foreground. The strength map provides vital information about new fragments appearing in the scene, thereby assisting in addressing problematic cases like self-occlusion. The strength map is used by the region growing formulation, reminiscent of discrete level set implementation, to extract accurate boundaries of the target. Significant speedup is achieved using the region growing procedure over traditional level set based methods. The joint Lucas-Kanade feature tracking approach is also incorporated for handling large unpredictable motions even in untextured regions. Experimental results on a number of challenging sequences demonstrate the effectiveness of the technique."],"dc:identifier":["https://open.clemson.edu/all_theses/643"],"dc:subject":["Fragment","Gaussian mixture models","level sets","Multi-Modal","Strength image","Tracking","Computer Sciences"],"dc:title":["Non-rigid multi-modal object tracking using Gaussian mixture models"],"thesis:degree_discipline":["Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:07:16Z"}