Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning

The study of human posture analysis and gait event detection from various types of inputs is a key contribution to the human life log. With the help of this research and technologies humans can save costs in terms of time and utility resources. In this paper we present a robust approach to human pos...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yazeed Ghadi, Israr Akhter, Mohammed Alarfaj, Ahmad Jalal, Kibum Kim
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	2D to 3D reconstruction Convolutional neural network Gait event classification Human posture analysis Landmark detection Synthetic model Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/27a4025cbc82419297e4590b08f1aa2f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:27a4025cbc82419297e4590b08f1aa2f
record_format	dspace
spelling	oai:doaj.org-article:27a4025cbc82419297e4590b08f1aa2f2021-11-21T15:05:12ZSyntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning10.7717/peerj-cs.7642376-5992https://doaj.org/article/27a4025cbc82419297e4590b08f1aa2f2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-764.pdfhttps://peerj.com/articles/cs-764/https://doaj.org/toc/2376-5992The study of human posture analysis and gait event detection from various types of inputs is a key contribution to the human life log. With the help of this research and technologies humans can save costs in terms of time and utility resources. In this paper we present a robust approach to human posture analysis and gait event detection from complex video-based data. For this, initially posture information, landmark information are extracted, and human 2D skeleton mesh are extracted, using this information set we reconstruct the human 2D to 3D model. Contextual features, namely, degrees of freedom over detected body parts, joint angle information, periodic and non-periodic motion, and human motion direction flow, are extracted. For features mining, we applied the rule-based features mining technique and, for gait event detection and classification, the deep learning-based CNN technique is applied over the mpii-video pose, the COCO, and the pose track datasets. For the mpii-video pose dataset, we achieved a human landmark detection mean accuracy of 87.09% and a gait event recognition mean accuracy of 90.90%. For the COCO dataset, we achieved a human landmark detection mean accuracy of 87.36% and a gait event recognition mean accuracy of 89.09%. For the pose track dataset, we achieved a human landmark detection mean accuracy of 87.72% and a gait event recognition mean accuracy of 88.18%. The proposed system performance shows a significant improvement compared to existing state-of-the-art frameworks.Yazeed GhadiIsrar AkhterMohammed AlarfajAhmad JalalKibum KimPeerJ Inc.article2D to 3D reconstructionConvolutional neural networkGait event classificationHuman posture analysisLandmark detectionSynthetic modelElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e764 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	2D to 3D reconstruction Convolutional neural network Gait event classification Human posture analysis Landmark detection Synthetic model Electronic computers. Computer science QA75.5-76.95
spellingShingle	2D to 3D reconstruction Convolutional neural network Gait event classification Human posture analysis Landmark detection Synthetic model Electronic computers. Computer science QA75.5-76.95 Yazeed Ghadi Israr Akhter Mohammed Alarfaj Ahmad Jalal Kibum Kim Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
description	The study of human posture analysis and gait event detection from various types of inputs is a key contribution to the human life log. With the help of this research and technologies humans can save costs in terms of time and utility resources. In this paper we present a robust approach to human posture analysis and gait event detection from complex video-based data. For this, initially posture information, landmark information are extracted, and human 2D skeleton mesh are extracted, using this information set we reconstruct the human 2D to 3D model. Contextual features, namely, degrees of freedom over detected body parts, joint angle information, periodic and non-periodic motion, and human motion direction flow, are extracted. For features mining, we applied the rule-based features mining technique and, for gait event detection and classification, the deep learning-based CNN technique is applied over the mpii-video pose, the COCO, and the pose track datasets. For the mpii-video pose dataset, we achieved a human landmark detection mean accuracy of 87.09% and a gait event recognition mean accuracy of 90.90%. For the COCO dataset, we achieved a human landmark detection mean accuracy of 87.36% and a gait event recognition mean accuracy of 89.09%. For the pose track dataset, we achieved a human landmark detection mean accuracy of 87.72% and a gait event recognition mean accuracy of 88.18%. The proposed system performance shows a significant improvement compared to existing state-of-the-art frameworks.
format	article
author	Yazeed Ghadi Israr Akhter Mohammed Alarfaj Ahmad Jalal Kibum Kim
author_facet	Yazeed Ghadi Israr Akhter Mohammed Alarfaj Ahmad Jalal Kibum Kim
author_sort	Yazeed Ghadi
title	Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
title_short	Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
title_full	Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
title_fullStr	Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
title_full_unstemmed	Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning
title_sort	syntactic model-based human body 3d reconstruction and event classification via association based features mining and deep learning
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/27a4025cbc82419297e4590b08f1aa2f
work_keys_str_mv	AT yazeedghadi syntacticmodelbasedhumanbody3dreconstructionandeventclassificationviaassociationbasedfeaturesmininganddeeplearning AT israrakhter syntacticmodelbasedhumanbody3dreconstructionandeventclassificationviaassociationbasedfeaturesmininganddeeplearning AT mohammedalarfaj syntacticmodelbasedhumanbody3dreconstructionandeventclassificationviaassociationbasedfeaturesmininganddeeplearning AT ahmadjalal syntacticmodelbasedhumanbody3dreconstructionandeventclassificationviaassociationbasedfeaturesmininganddeeplearning AT kibumkim syntacticmodelbasedhumanbody3dreconstructionandeventclassificationviaassociationbasedfeaturesmininganddeeplearning
_version_	1718418813834231808

Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning

Ejemplares similares