{"id":{"repo_id":"umkc","oai_identifier":"oai:mospace.umsystem.edu:10355/100721"},"canonical_url":"https://search.dev.ndltd.org/etd/umkc/oai:mospace.umsystem.edu:10355/100721","repository":{"repo_id":"umkc","name":"University of Missouri - Kansas City","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Improving robustness of gait recognition based on deep learning","abstract":"Gait recognition is a technology that identifies human ID according to the human unique biometric gait feature. It has two popular categories. One category of gait recognition methods is appearance-based algorithms, which usually extracts human silhouettes as the initial input feature and achieves high recognition rates. However, the silhouette-based feature is easily affected by the view, clothing, bag, and other external variations. Another category is based on model-based algorithms, one popular model-based feature is extracted from human skeletons. The skeleton-based feature is robust to many variations because it is less sensitive to human shape. However, the performance of skeleton-based methods suffers from recognition accuracy loss due to limited input information. This thesis proposes multiple deep learning-based frameworks to address multiple issues for the appearance-based methods and model-based methods. In each case, the proposed methods achieve high results with significant improvement to the current technologies.","abstract_html":"Gait recognition is a technology that identifies human ID according to the human unique biometric gait feature. It has two popular categories. One category of gait recognition methods is appearance-based algorithms, which usually extracts human silhouettes as the initial input feature and achieves high recognition rates. However, the silhouette-based feature is easily affected by the view, clothing, bag, and other external variations. Another category is based on model-based algorithms, one popular model-based feature is extracted from human skeletons. The skeleton-based feature is robust to many variations because it is less sensitive to human shape. However, the performance of skeleton-based methods suffers from recognition accuracy loss due to limited input information. This thesis proposes multiple deep learning-based frameworks to address multiple issues for the appearance-based methods and model-based methods. In each case, the proposed methods achieve high results with significant improvement to the current technologies.","abstract_has_math":false,"creators":["Liao, Rijun"],"institution":"University of Missouri--Kansas City","degree_name":"Ph.D. (Doctor of Philosophy)","degree_level":"Doctoral","degree_discipline":"Computer Networking and Communication Systems (UMKC)","degree_department":null,"school":null,"contributors":[],"advisors":["Li, Zhu","Song, Sejun"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-24T05:19:15Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/100721","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Li, Zhu","Song, Sejun"]},{"key":"dc:creator","label":"Author","values":["Liao, Rijun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-05-07T22:01:54Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-05-07T22:01:54Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Networking and Communication Systems (UMKC)","Electrical and Computer Engineering (UMKC)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D. (Doctor of Philosophy)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Kansas City"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/100721"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Dissertation (Ph.D)--Department of Computer Science and Electrical Engineering. University of Missouri--Kansas City, 2024","Title from PDF of title page, viewed March 6, 2026","Dissertation advisors: Zhu Li and Sejun Song","Vita","Includes bibliographical references (pages 116-128)"]},{"key":"dc:description.abstract","label":"Abstract","values":["Gait recognition is a technology that identifies human ID according to the human unique biometric gait feature. It has two popular categories. One category of gait recognition methods is appearance-based algorithms, which usually extracts human silhouettes as the initial input feature and achieves high recognition rates. However, the silhouette-based feature is easily affected by the view, clothing, bag, and other external variations. Another category is based on model-based algorithms, one popular model-based feature is extracted from human skeletons. The skeleton-based feature is robust to many variations because it is less sensitive to human shape. However, the performance of skeleton-based methods suffers from recognition accuracy loss due to limited input information. This thesis proposes multiple deep learning-based frameworks to address multiple issues for the appearance-based methods and model-based methods. In each case, the proposed methods achieve high results with significant improvement to the current technologies."]},{"key":"dc:title","label":"Title","values":["Improving robustness of gait recognition based on deep learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Li, Zhu","Song, Sejun"],"dc:creator":["Liao, Rijun"],"dc:date.accessioned":["2024-05-07T22:01:54Z"],"dc:date.available":["2024-05-07T22:01:54Z"],"dc:date.issued":["2024"],"dc:description":["Dissertation (Ph.D)--Department of Computer Science and Electrical Engineering. University of Missouri--Kansas City, 2024","Title from PDF of title page, viewed March 6, 2026","Dissertation advisors: Zhu Li and Sejun Song","Vita","Includes bibliographical references (pages 116-128)"],"dc:description.abstract":["Gait recognition is a technology that identifies human ID according to the human unique biometric gait feature. It has two popular categories. One category of gait recognition methods is appearance-based algorithms, which usually extracts human silhouettes as the initial input feature and achieves high recognition rates. However, the silhouette-based feature is easily affected by the view, clothing, bag, and other external variations. Another category is based on model-based algorithms, one popular model-based feature is extracted from human skeletons. The skeleton-based feature is robust to many variations because it is less sensitive to human shape. However, the performance of skeleton-based methods suffers from recognition accuracy loss due to limited input information. This thesis proposes multiple deep learning-based frameworks to address multiple issues for the appearance-based methods and model-based methods. In each case, the proposed methods achieve high results with significant improvement to the current technologies."],"dc:identifier.uri":["https://hdl.handle.net/10355/100721"],"dc:title":["Improving robustness of gait recognition based on deep learning"],"thesis:degree_discipline":["Computer Networking and Communication Systems (UMKC)","Electrical and Computer Engineering (UMKC)"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Ph.D. (Doctor of Philosophy)"],"thesis:institution_name":["University of Missouri--Kansas City"]},"updated_at":"2026-07-24T05:19:15Z"}