Gait measurement system for the multi-target stepping task using a laser range sensor

Ayanori Yorozu, Shu Nishiguchi, Minoru Yamada, Tomoki Aoyama, Toshiki Moriguchi, Masaki Takahashi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

For the prevention of falling in the elderly, gait training has been proposed using tasks such as the multi-target stepping task (MTST), in which participants step on assigned colored targets. This study presents a gait measurement system using a laser range sensor for the MTST to evaluate the risk of falling. The system tracks both legs and measures general walking parameters such as stride length and walking speed. Additionally, it judges whether the participant steps on the assigned colored targets and detects cross steps to evaluate cognitive function. However, situations in which one leg is hidden from the sensor or the legs are close occur and are likely to lead to losing track of the legs or false tracking. To solve these problems, we propose a novel leg detection method with five observed leg patterns and global nearest neighbor-based data association with a variable validation region based on the state of each leg. In addition, methods to judge target steps and detect cross steps based on leg trajectory are proposed. From the experimental results with the elderly, it is confirmed that the proposed system can improve leg-tracking performance, judge target steps and detect cross steps with high accuracy.

Original languageEnglish
Pages (from-to)11151-11168
Number of pages18
JournalSensors (Switzerland)
Volume15
Issue number5
DOIs
Publication statusPublished - 2015

Fingerprint

gait
Gait
Leg
Lasers
sensors
Sensors
lasers
Trajectories
Accidental Falls
walking
falling
education
trajectories
Cognition
Walking

Keywords

  • data association
  • gait measurement
  • Kalman filter
  • laser range sensor

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Gait measurement system for the multi-target stepping task using a laser range sensor. / Yorozu, Ayanori; Nishiguchi, Shu; Yamada, Minoru; Aoyama, Tomoki; Moriguchi, Toshiki; Takahashi, Masaki.

In: Sensors (Switzerland), Vol. 15, No. 5, 2015, p. 11151-11168.

Research output: Contribution to journalArticle

Yorozu, A, Nishiguchi, S, Yamada, M, Aoyama, T, Moriguchi, T & Takahashi, M 2015, 'Gait measurement system for the multi-target stepping task using a laser range sensor', Sensors (Switzerland), vol. 15, no. 5, pp. 11151-11168. https://doi.org/10.3390/s150511151
Yorozu, Ayanori ; Nishiguchi, Shu ; Yamada, Minoru ; Aoyama, Tomoki ; Moriguchi, Toshiki ; Takahashi, Masaki. / Gait measurement system for the multi-target stepping task using a laser range sensor. In: Sensors (Switzerland). 2015 ; Vol. 15, No. 5. pp. 11151-11168.
@article{9d4569a6d2e64327bfedfa9febdf829c,
title = "Gait measurement system for the multi-target stepping task using a laser range sensor",
abstract = "For the prevention of falling in the elderly, gait training has been proposed using tasks such as the multi-target stepping task (MTST), in which participants step on assigned colored targets. This study presents a gait measurement system using a laser range sensor for the MTST to evaluate the risk of falling. The system tracks both legs and measures general walking parameters such as stride length and walking speed. Additionally, it judges whether the participant steps on the assigned colored targets and detects cross steps to evaluate cognitive function. However, situations in which one leg is hidden from the sensor or the legs are close occur and are likely to lead to losing track of the legs or false tracking. To solve these problems, we propose a novel leg detection method with five observed leg patterns and global nearest neighbor-based data association with a variable validation region based on the state of each leg. In addition, methods to judge target steps and detect cross steps based on leg trajectory are proposed. From the experimental results with the elderly, it is confirmed that the proposed system can improve leg-tracking performance, judge target steps and detect cross steps with high accuracy.",
keywords = "data association, gait measurement, Kalman filter, laser range sensor",
author = "Ayanori Yorozu and Shu Nishiguchi and Minoru Yamada and Tomoki Aoyama and Toshiki Moriguchi and Masaki Takahashi",
year = "2015",
doi = "10.3390/s150511151",
language = "English",
volume = "15",
pages = "11151--11168",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "5",

}

TY - JOUR

T1 - Gait measurement system for the multi-target stepping task using a laser range sensor

AU - Yorozu, Ayanori

AU - Nishiguchi, Shu

AU - Yamada, Minoru

AU - Aoyama, Tomoki

AU - Moriguchi, Toshiki

AU - Takahashi, Masaki

PY - 2015

Y1 - 2015

N2 - For the prevention of falling in the elderly, gait training has been proposed using tasks such as the multi-target stepping task (MTST), in which participants step on assigned colored targets. This study presents a gait measurement system using a laser range sensor for the MTST to evaluate the risk of falling. The system tracks both legs and measures general walking parameters such as stride length and walking speed. Additionally, it judges whether the participant steps on the assigned colored targets and detects cross steps to evaluate cognitive function. However, situations in which one leg is hidden from the sensor or the legs are close occur and are likely to lead to losing track of the legs or false tracking. To solve these problems, we propose a novel leg detection method with five observed leg patterns and global nearest neighbor-based data association with a variable validation region based on the state of each leg. In addition, methods to judge target steps and detect cross steps based on leg trajectory are proposed. From the experimental results with the elderly, it is confirmed that the proposed system can improve leg-tracking performance, judge target steps and detect cross steps with high accuracy.

AB - For the prevention of falling in the elderly, gait training has been proposed using tasks such as the multi-target stepping task (MTST), in which participants step on assigned colored targets. This study presents a gait measurement system using a laser range sensor for the MTST to evaluate the risk of falling. The system tracks both legs and measures general walking parameters such as stride length and walking speed. Additionally, it judges whether the participant steps on the assigned colored targets and detects cross steps to evaluate cognitive function. However, situations in which one leg is hidden from the sensor or the legs are close occur and are likely to lead to losing track of the legs or false tracking. To solve these problems, we propose a novel leg detection method with five observed leg patterns and global nearest neighbor-based data association with a variable validation region based on the state of each leg. In addition, methods to judge target steps and detect cross steps based on leg trajectory are proposed. From the experimental results with the elderly, it is confirmed that the proposed system can improve leg-tracking performance, judge target steps and detect cross steps with high accuracy.

KW - data association

KW - gait measurement

KW - Kalman filter

KW - laser range sensor

UR - http://www.scopus.com/inward/record.url?scp=84965086067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965086067&partnerID=8YFLogxK

U2 - 10.3390/s150511151

DO - 10.3390/s150511151

M3 - Article

C2 - 25985161

AN - SCOPUS:84929352856

VL - 15

SP - 11151

EP - 11168

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 5

ER -