The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
L'analyse de la marche humaine a été largement utilisée dans les domaines médicaux et de la santé. Il est essentiel d'extraire les caractéristiques spatio-temporelles de la démarche (par exemple, la durée d'un seul appui, la longueur du pas et l'angle des orteils) en divisant la phase de marche et en estimant la position/orientation de l'empreinte dans ces champs. Par conséquent, nous proposons une méthode pour partitionner la phase de marche en fonction d'une séquence de positions du pied en utilisant une approximation linéaire par morceaux mutuellement contrainte avec une programmation dynamique, qui représente non seulement bien la démarche normale mais également la démarche pathologique sans données d'entraînement. Nous proposons également une méthode de détection des empreintes de pas en accumulant les bords des orteils sur le plan du sol pendant les phases d'appui, ce qui nous permet de détecter les empreintes de pas plus clairement qu'une méthode conventionnelle. Enfin, nous extrayons quatre paramètres spatiaux/temporels de démarche pour évaluer la précision : durée d’appui simple, durée d’appui double, angle d’orteil et longueur de pas. Nous avons mené des expériences pour valider la méthode proposée en utilisant deux types de modèles de démarche, à savoir une démarche hémiplégique saine et imitée, auprès de 10 sujets. Nous avons confirmé que la méthode proposée pouvait estimer les paramètres spatiaux/temporels de la démarche avec plus de précision qu'une méthode conventionnelle basée sur le squelette, quel que soit le modèle de démarche.
Makoto YASUKAWA
Osaka University
Yasushi MAKIHARA
Osaka University
Toshinori HOSOI
NEC Corporation
Masahiro KUBO
NEC Corporation
Yasushi YAGI
Osaka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Makoto YASUKAWA, Yasushi MAKIHARA, Toshinori HOSOI, Masahiro KUBO, Yasushi YAGI, "Gait Phase Partitioning and Footprint Detection Using Mutually Constrained Piecewise Linear Approximation with Dynamic Programming" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 11, pp. 1951-1962, November 2021, doi: 10.1587/transinf.2020ZDP7503.
Abstract: Human gait analysis has been widely used in medical and health fields. It is essential to extract spatio-temporal gait features (e.g., single support duration, step length, and toe angle) by partitioning the gait phase and estimating the footprint position/orientation in such fields. Therefore, we propose a method to partition the gait phase given a foot position sequence using mutually constrained piecewise linear approximation with dynamic programming, which not only represents normal gait well but also pathological gait without training data. We also propose a method to detect footprints by accumulating toe edges on the floor plane during stance phases, which enables us to detect footprints more clearly than a conventional method. Finally, we extract four spatial/temporal gait parameters for accuracy evaluation: single support duration, double support duration, toe angle, and step length. We conducted experiments to validate the proposed method using two types of gait patterns, that is, healthy and mimicked hemiplegic gait, from 10 subjects. We confirmed that the proposed method could estimate the spatial/temporal gait parameters more accurately than a conventional skeleton-based method regardless of the gait pattern.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020ZDP7503/_p
Copier
@ARTICLE{e104-d_11_1951,
author={Makoto YASUKAWA, Yasushi MAKIHARA, Toshinori HOSOI, Masahiro KUBO, Yasushi YAGI, },
journal={IEICE TRANSACTIONS on Information},
title={Gait Phase Partitioning and Footprint Detection Using Mutually Constrained Piecewise Linear Approximation with Dynamic Programming},
year={2021},
volume={E104-D},
number={11},
pages={1951-1962},
abstract={Human gait analysis has been widely used in medical and health fields. It is essential to extract spatio-temporal gait features (e.g., single support duration, step length, and toe angle) by partitioning the gait phase and estimating the footprint position/orientation in such fields. Therefore, we propose a method to partition the gait phase given a foot position sequence using mutually constrained piecewise linear approximation with dynamic programming, which not only represents normal gait well but also pathological gait without training data. We also propose a method to detect footprints by accumulating toe edges on the floor plane during stance phases, which enables us to detect footprints more clearly than a conventional method. Finally, we extract four spatial/temporal gait parameters for accuracy evaluation: single support duration, double support duration, toe angle, and step length. We conducted experiments to validate the proposed method using two types of gait patterns, that is, healthy and mimicked hemiplegic gait, from 10 subjects. We confirmed that the proposed method could estimate the spatial/temporal gait parameters more accurately than a conventional skeleton-based method regardless of the gait pattern.},
keywords={},
doi={10.1587/transinf.2020ZDP7503},
ISSN={1745-1361},
month={November},}
Copier
TY - JOUR
TI - Gait Phase Partitioning and Footprint Detection Using Mutually Constrained Piecewise Linear Approximation with Dynamic Programming
T2 - IEICE TRANSACTIONS on Information
SP - 1951
EP - 1962
AU - Makoto YASUKAWA
AU - Yasushi MAKIHARA
AU - Toshinori HOSOI
AU - Masahiro KUBO
AU - Yasushi YAGI
PY - 2021
DO - 10.1587/transinf.2020ZDP7503
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2021
AB - Human gait analysis has been widely used in medical and health fields. It is essential to extract spatio-temporal gait features (e.g., single support duration, step length, and toe angle) by partitioning the gait phase and estimating the footprint position/orientation in such fields. Therefore, we propose a method to partition the gait phase given a foot position sequence using mutually constrained piecewise linear approximation with dynamic programming, which not only represents normal gait well but also pathological gait without training data. We also propose a method to detect footprints by accumulating toe edges on the floor plane during stance phases, which enables us to detect footprints more clearly than a conventional method. Finally, we extract four spatial/temporal gait parameters for accuracy evaluation: single support duration, double support duration, toe angle, and step length. We conducted experiments to validate the proposed method using two types of gait patterns, that is, healthy and mimicked hemiplegic gait, from 10 subjects. We confirmed that the proposed method could estimate the spatial/temporal gait parameters more accurately than a conventional skeleton-based method regardless of the gait pattern.
ER -