{"id":{"repo_id":"denver","oai_identifier":"oai:digitalcommons.du.edu:etd-2169"},"canonical_url":"https://search.ndltd.org/etd/denver/oai:digitalcommons.du.edu:etd-2169","repository":{"repo_id":"denver","name":"University of Denver","base_url":"https://digitalcommons.du.edu/do/oai/"},"display":{"title":"Ultra-Wideband Radar Based Human Motion Analysis","abstract":"This thesis proposes and investigates two techniques in ultra-wideband (UWB) radar based human motion analysis. The first one is accurate human body landmark detection using UWB radars. The detection is achieved by moving target indication (MTI) and constant false alarm rate detection (CFAR). A new CFAR detection technique is proposed, namely the out-of-band (OB) CFAR detection. In the field experiment, two RF reflective markers are attached to the wrist and elbow of one human arm for reflecting radar signals. It is demonstrated that detection of two markers are feasible and successfully achieved. And our results suggests the OB-CFAR performs better than conventional CFAR in landmark detection. The second technique aims to study on the human motion classification through the exploitation of video and radar data, respectively. Motion history image (MHI) and Hu moment method are applied to extract temporal features from video clips. Principal component analysis (PCA) is used to obtain radar detection [signatures]. We use k-means clusters to quantize the observation feature vectors. Hidden Markov models (HMMs) are trained with the features extracted from both video and radar data to discern the motion types. Experiment results indicate that the proposed approach can provide improved performance in distinguishing fall motions from other motions such as sitting.","abstract_html":"This thesis proposes and investigates two techniques in ultra-wideband (UWB) radar based human motion analysis. The first one is accurate human body landmark detection using UWB radars. The detection is achieved by moving target indication (MTI) and constant false alarm rate detection (CFAR). A new CFAR detection technique is proposed, namely the out-of-band (OB) CFAR detection. In the field experiment, two RF reflective markers are attached to the wrist and elbow of one human arm for reflecting radar signals. It is demonstrated that detection of two markers are feasible and successfully achieved. And our results suggests the OB-CFAR performs better than conventional CFAR in landmark detection. The second technique aims to study on the human motion classification through the exploitation of video and radar data, respectively. Motion history image (MHI) and Hu moment method are applied to extract temporal features from video clips. Principal component analysis (PCA) is used to obtain radar detection [signatures]. We use k-means clusters to quantize the observation feature vectors. Hidden Markov models (HMMs) are trained with the features extracted from both video and radar data to discern the motion types. Experiment results indicate that the proposed approach can provide improved performance in distinguishing fall motions from other motions such as sitting.","abstract_has_math":false,"creators":["Zhou, Zhichong"],"institution":null,"degree_name":"M.S.","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Jun Zhang, Ph.D.","Nathan Sturtevant","Wenzhong Gao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:53:26Z","subjects":["CFAR","Constant false alarm rate detection","Human motion classification","Landmark detection","UWB radar","Ultra-wideband radar","Biomedical Engineering and Bioengineering","Engineering"],"languages":["en"],"rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>","Zhichong Zhou"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.du.edu/etd/1169","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.du.edu/etd/1169","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.du.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.du.edu%3Aetd-2169","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jun Zhang, Ph.D.","Nathan Sturtevant","Wenzhong Gao"]},{"key":"dc:creator","label":"Author","values":["Zhou, Zhichong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2017-02-17T08:00:00Z"]},{"key":"dc:date.copyright","label":"Dc Date Copyright","values":["2016-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2016-01-01T08:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["CFAR","Constant false alarm rate detection","Human motion classification","Landmark detection","UWB radar","Ultra-wideband radar","Biomedical Engineering and Bioengineering","Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"]},{"key":"dc:rights.holder","label":"Dc Rights Holder","values":["Zhichong Zhou"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.du.edu/etd/1169"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis proposes and investigates two techniques in ultra-wideband (UWB) radar based human motion analysis. The first one is accurate human body landmark detection using UWB radars. The detection is achieved by moving target indication (MTI) and constant false alarm rate detection (CFAR). A new CFAR detection technique is proposed, namely the out-of-band (OB) CFAR detection. In the field experiment, two RF reflective markers are attached to the wrist and elbow of one human arm for reflecting radar signals. It is demonstrated that detection of two markers are feasible and successfully achieved. And our results suggests the OB-CFAR performs better than conventional CFAR in landmark detection. The second technique aims to study on the human motion classification through the exploitation of video and radar data, respectively. Motion history image (MHI) and Hu moment method are applied to extract temporal features from video clips. Principal component analysis (PCA) is used to obtain radar detection [signatures]. We use k-means clusters to quantize the observation feature vectors. Hidden Markov models (HMMs) are trained with the features extracted from both video and radar data to discern the motion types. Experiment results indicate that the proposed approach can provide improved performance in distinguishing fall motions from other motions such as sitting."]},{"key":"dc:description.provenance","label":"Dc Description Provenance","values":["Received from ProQuest"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:format.extent","label":"Dc Format Extent","values":["60 p."]},{"key":"dc:title","label":"Title","values":["Ultra-Wideband Radar Based Human Motion Analysis"]}]}],"canonical_facts":{"dc:contributor":["Jun Zhang, Ph.D.","Nathan Sturtevant","Wenzhong Gao"],"dc:creator":["Zhou, Zhichong"],"dc:date.available":["2017-02-17T08:00:00Z"],"dc:date.copyright":["2016-01-01T08:00:00Z"],"dc:date.created":["2016-01-01T08:00:00Z"],"dc:description.abstract":["This thesis proposes and investigates two techniques in ultra-wideband (UWB) radar based human motion analysis. The first one is accurate human body landmark detection using UWB radars. The detection is achieved by moving target indication (MTI) and constant false alarm rate detection (CFAR). A new CFAR detection technique is proposed, namely the out-of-band (OB) CFAR detection. In the field experiment, two RF reflective markers are attached to the wrist and elbow of one human arm for reflecting radar signals. It is demonstrated that detection of two markers are feasible and successfully achieved. And our results suggests the OB-CFAR performs better than conventional CFAR in landmark detection. The second technique aims to study on the human motion classification through the exploitation of video and radar data, respectively. Motion history image (MHI) and Hu moment method are applied to extract temporal features from video clips. Principal component analysis (PCA) is used to obtain radar detection [signatures]. We use k-means clusters to quantize the observation feature vectors. Hidden Markov models (HMMs) are trained with the features extracted from both video and radar data to discern the motion types. Experiment results indicate that the proposed approach can provide improved performance in distinguishing fall motions from other motions such as sitting."],"dc:description.provenance":["Received from ProQuest"],"dc:format":["application/pdf"],"dc:format.extent":["60 p."],"dc:identifier":["https://digitalcommons.du.edu/etd/1169"],"dc:language":["en"],"dc:rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"],"dc:rights.holder":["Zhichong Zhou"],"dc:subject":["CFAR","Constant false alarm rate detection","Human motion classification","Landmark detection","UWB radar","Ultra-wideband radar","Biomedical Engineering and Bioengineering","Engineering"],"dc:title":["Ultra-Wideband Radar Based Human Motion Analysis"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["M.S."]},"updated_at":"2026-11-19T07:53:26Z"}