{"id":875,"date":"2016-07-12T15:13:54","date_gmt":"2016-07-12T15:13:54","guid":{"rendered":"https:\/\/sites.wp.odu.edu\/VisionLab\/?page_id=875"},"modified":"2023-03-15T14:04:52","modified_gmt":"2023-03-15T14:04:52","slug":"gender-classification-using-gait-kinematics","status":"publish","type":"page","link":"https:\/\/sites.wp.odu.edu\/VisionLab\/research\/gender-classification-using-gait-kinematics\/","title":{"rendered":"Gender Classification Using Gait Kinematics"},"content":{"rendered":"<p>In this work, we exploit nonpathological gait kinematics<br \/> to improve gender classification from motion information<br \/> using large-scale datasets with subjects moving in a less controlled<br \/> environment. Dynamic motion features are extracted from motion<br \/> capture data using principal component analysis. Features are further<br \/> refined in the time and spatial domain by exploiting gait phase<br \/> cycles and significant body part indicators obtained from analyzing<br \/> nonpathological gait kinematics. Classification is performed<br \/> using support vector machine with a radial basis function. Experimental<br \/> testing with a dataset of 49 subjects reveals that human<br \/> gender classification rates are improved from 73% to 93% using<br \/> leave-one-out cross validation.<\/p> <p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-877\" src=\"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-content\/uploads\/sites\/1499\/2016\/07\/point_figure.png\" alt=\"point_figure\" width=\"742\" height=\"498\" srcset=\"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-content\/uploads\/sites\/1499\/2016\/07\/point_figure.png 742w, https:\/\/sites.wp.odu.edu\/VisionLab\/wp-content\/uploads\/sites\/1499\/2016\/07\/point_figure-300x201.png 300w, https:\/\/sites.wp.odu.edu\/VisionLab\/wp-content\/uploads\/sites\/1499\/2016\/07\/point_figure-272x182.png 272w\" sizes=\"(max-width: 742px) 100vw, 742px\" \/><\/p> <p>Three-dimensional visualization of joint center data from TRC data frame.<\/p> ","protected":false},"excerpt":{"rendered":"<p>In this work, we exploit nonpathological gait kinematics to improve gender classification from motion information using large-scale datasets with subjects moving in a less controlled environment. Dynamic motion features are extracted from motion capture data using principal component analysis. Features are further refined in the time and spatial domain by exploiting gait phase cycles and [&hellip;]<\/p>\n","protected":false},"author":5165,"featured_media":0,"parent":35,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"_links":{"self":[{"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/pages\/875"}],"collection":[{"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/users\/5165"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/comments?post=875"}],"version-history":[{"count":5,"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/pages\/875\/revisions"}],"predecessor-version":[{"id":2304,"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/pages\/875\/revisions\/2304"}],"up":[{"embeddable":true,"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/pages\/35"}],"wp:attachment":[{"href":"https:\/\/sites.wp.odu.edu\/VisionLab\/wp-json\/wp\/v2\/media?parent=875"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}