{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-1337"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-1337","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Background subtraction using ensembles of classifiers with an extended feature set","abstract":"The limitations of foreground segmentation in difficult environments using standard color space features often result in poor performance during autonomous tracking. This work presents a new approach for classification of foreground and background pixels in image sequences by employing an ensemble of classifiers, each operating on a different feature type such as the three RGB features, gradient magnitude and orientation features, and eight Haar features. These thirteen features are used in an ensemble classifier where each classifier operates on a single image feature. Each classifier implements a Mixture of Gaussians-based unsupervised background classification algorithm. The non-thresholded, classification decision score of each classifier are fused together by taking the average of their outputs and creating one single hypothesis. The results of using the ensemble classifier on three separate and distinct data sets are compared to using only RGB features through ROC graphs. The extended feature vector outperforms the RGB features on all three data sets, and shows a large scale improvement on two of the three data sets. The two data sets with the greatest improvements are both outdoor data sets with global illumination changes and the other has many local illumination changes. When using the entire feature set, to operate at a 90% true positive rate, the per pixel, false alarm rate is reduced five times in one data set and six times in the other data set.","abstract_html":"The limitations of foreground segmentation in difficult environments using standard color space features often result in poor performance during autonomous tracking. This work presents a new approach for classification of foreground and background pixels in image sequences by employing an ensemble of classifiers, each operating on a different feature type such as the three RGB features, gradient magnitude and orientation features, and eight Haar features. These thirteen features are used in an ensemble classifier where each classifier operates on a single image feature. Each classifier implements a Mixture of Gaussians-based unsupervised background classification algorithm. The non-thresholded, classification decision score of each classifier are fused together by taking the average of their outputs and creating one single hypothesis. The results of using the ensemble classifier on three separate and distinct data sets are compared to using only RGB features through ROC graphs. The extended feature vector outperforms the RGB features on all three data sets, and shows a large scale improvement on two of the three data sets. The two data sets with the greatest improvements are both outdoor data sets with global illumination changes and the other has many local illumination changes. When using the entire feature set, to operate at a 90% true positive rate, the per pixel, false alarm rate is reduced five times in one data set and six times in the other data set.","abstract_has_math":false,"creators":["Klare, Brendan F"],"institution":"University of South Florida","degree_name":null,"degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Sudeep Sarkar, Ph.D.","Lawrence O. Hall, Ph.D.","Dmitry B. Goldgof, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2008,"date_issued":"2008-06-30T07:00:00Z","date_published":"2008-06-30T07:00:00Z","updated_at":"2026-11-19T08:33:23Z","subjects":["Tracking","Classification","Segmentation","Fusion","Illumination invariant","American Studies","Arts and Humanities"],"languages":["EN-US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/338","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/338","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://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-1337","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sudeep Sarkar, Ph.D.","Lawrence O. Hall, Ph.D.","Dmitry B. Goldgof, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Klare, Brendan F"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2008-06-30T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.C.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Tracking","Classification","Segmentation","Fusion","Illumination invariant","American Studies","Arts and Humanities"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["EN-US"]},{"key":"dc:rights.license","label":"Dc Rights License","values":["default"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/338"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The limitations of foreground segmentation in difficult environments using standard color space features often result in poor performance during autonomous tracking. This work presents a new approach for classification of foreground and background pixels in image sequences by employing an ensemble of classifiers, each operating on a different feature type such as the three RGB features, gradient magnitude and orientation features, and eight Haar features. These thirteen features are used in an ensemble classifier where each classifier operates on a single image feature. Each classifier implements a Mixture of Gaussians-based unsupervised background classification algorithm. The non-thresholded, classification decision score of each classifier are fused together by taking the average of their outputs and creating one single hypothesis. The results of using the ensemble classifier on three separate and distinct data sets are compared to using only RGB features through ROC graphs. The extended feature vector outperforms the RGB features on all three data sets, and shows a large scale improvement on two of the three data sets. The two data sets with the greatest improvements are both outdoor data sets with global illumination changes and the other has many local illumination changes. When using the entire feature set, to operate at a 90% true positive rate, the per pixel, false alarm rate is reduced five times in one data set and six times in the other data set."]},{"key":"dc:title","label":"Title","values":["Background subtraction using ensembles of classifiers with an extended feature set"]}]}],"canonical_facts":{"dc:contributor":["Sudeep Sarkar, Ph.D.","Lawrence O. Hall, Ph.D.","Dmitry B. Goldgof, Ph.D."],"dc:creator":["Klare, Brendan F"],"dc:date":["2008-06-30T07:00:00Z"],"dc:description":["The limitations of foreground segmentation in difficult environments using standard color space features often result in poor performance during autonomous tracking. This work presents a new approach for classification of foreground and background pixels in image sequences by employing an ensemble of classifiers, each operating on a different feature type such as the three RGB features, gradient magnitude and orientation features, and eight Haar features. These thirteen features are used in an ensemble classifier where each classifier operates on a single image feature. Each classifier implements a Mixture of Gaussians-based unsupervised background classification algorithm. The non-thresholded, classification decision score of each classifier are fused together by taking the average of their outputs and creating one single hypothesis. The results of using the ensemble classifier on three separate and distinct data sets are compared to using only RGB features through ROC graphs. The extended feature vector outperforms the RGB features on all three data sets, and shows a large scale improvement on two of the three data sets. The two data sets with the greatest improvements are both outdoor data sets with global illumination changes and the other has many local illumination changes. When using the entire feature set, to operate at a 90% true positive rate, the per pixel, false alarm rate is reduced five times in one data set and six times in the other data set."],"dc:identifier":["https://digitalcommons.usf.edu/etd/338"],"dc:language":["EN-US"],"dc:rights.license":["default"],"dc:subject":["Tracking","Classification","Segmentation","Fusion","Illumination invariant","American Studies","Arts and Humanities"],"dc:title":["Background subtraction using ensembles of classifiers with an extended feature set"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis","M.S.C.S."],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:33:23Z"}