{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recognizing-involuntary-actions-from-3d","title":"Recognizing Involuntary Actions from 3D Skeleton Data Using Body States","arxiv_id":"1708.06227","date":"2017-08-21","proceeding":null,"authors":["Mozhgan Mokari","Hoda Mohammadzade","Benyamin Ghojogh"],"abstract":"Human action recognition has been one of the most active fields of research\nin computer vision for last years. Two dimensional action recognition methods\nare facing serious challenges such as occlusion and missing the third dimension\nof data. Development of depth sensors has made it feasible to track positions\nof human body joints over time. This paper proposes a novel method of action\nrecognition which uses temporal 3D skeletal Kinect data. This method introduces\nthe definition of body states and then every action is modeled as a sequence of\nthese states. The learning stage uses Fisher Linear Discriminant Analysis (LDA)\nto construct discriminant feature space for discriminating the body states.\nMoreover, this paper suggests the use of the Mahalonobis distance as an\nappropriate distance metric for the classification of the states of involuntary\nactions. Hidden Markov Model (HMM) is then used to model the temporal\ntransition between the body states in each action. According to the results,\nthis method significantly outperforms other popular methods, with recognition\nrate of 88.64% for eight different actions and up to 96.18% for classifying\nfall actions.","url_abs":"http://arxiv.org/abs/1708.06227v1","url_pdf":"http://arxiv.org/pdf/1708.06227v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"recognizing-involuntary-actions-from-3d","repo_url":"https://github.com/bghojogh/Fisherposes","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}