Gait Estimation and Analysis from Noisy Observations

Hafsa Ismail, Ibrahim Radwan, Hanna Suominen, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

People’s walking style – their gait – can be an indicator of their health as it is affected by pain, illness, weakness, and aging. Gait analysis aims to detect gait variations. It is usually performed by an experienced observer with the help of different devices, such as cameras, sensors, and/or force plates. Frequent gait analysis, to observe changes over time, is costly and impractical. This paper initiates an inexpensive gait analysis based on recorded video. Our methodology first discusses estimating gait movements from predicted 2D joint locations that represent selected body parts from videos. Then, using a long-short-term memory (LSTM) regression model to predict 3D (Vicon) data, which was recorded simultaneously with the videos as ground truth. Feet movements estimated from video are highly correlated with the Vicon data, enabling gait analysis by measuring selected spatial gait parameters (step and cadence length, and walk base) from estimated movements. Using inexpensive and reliable cameras to record, estimate and analyse a person’s gait can be helpful; early detection of its changes facilitates early intervention.
Original languageEnglish
Title of host publication2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
EditorsRiccardo Barbieri
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2707-2712
Number of pages6
ISBN (Electronic)9781538613115
ISBN (Print)9781538613122
DOIs
Publication statusPublished - 2019
Event41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) - Berlin, Germany
Duration: 23 Jul 201927 Jul 2019
https://embc.embs.org/2019/

Conference

Conference41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Abbreviated titleEMBC 2019
CountryGermany
CityBerlin
Period23/07/1927/07/19
Internet address

Fingerprint

Gait analysis
Cameras
Aging of materials
Health
Sensors

Cite this

Ismail, H., Radwan, I., Suominen, H., & Goecke, R. (2019). Gait Estimation and Analysis from Noisy Observations. In R. Barbieri (Ed.), 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2707-2712). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2019.8857156
Ismail, Hafsa ; Radwan, Ibrahim ; Suominen, Hanna ; Goecke, Roland. / Gait Estimation and Analysis from Noisy Observations. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). editor / Riccardo Barbieri. IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 2707-2712
@inproceedings{6e679ec810ed4b3abd33c5626ec9b096,
title = "Gait Estimation and Analysis from Noisy Observations",
abstract = "People’s walking style – their gait – can be an indicator of their health as it is affected by pain, illness, weakness, and aging. Gait analysis aims to detect gait variations. It is usually performed by an experienced observer with the help of different devices, such as cameras, sensors, and/or force plates. Frequent gait analysis, to observe changes over time, is costly and impractical. This paper initiates an inexpensive gait analysis based on recorded video. Our methodology first discusses estimating gait movements from predicted 2D joint locations that represent selected body parts from videos. Then, using a long-short-term memory (LSTM) regression model to predict 3D (Vicon) data, which was recorded simultaneously with the videos as ground truth. Feet movements estimated from video are highly correlated with the Vicon data, enabling gait analysis by measuring selected spatial gait parameters (step and cadence length, and walk base) from estimated movements. Using inexpensive and reliable cameras to record, estimate and analyse a person’s gait can be helpful; early detection of its changes facilitates early intervention.",
keywords = "Human gait, Long Short-Term Memory",
author = "Hafsa Ismail and Ibrahim Radwan and Hanna Suominen and Roland Goecke",
year = "2019",
doi = "10.1109/EMBC.2019.8857156",
language = "English",
isbn = "9781538613122",
pages = "2707--2712",
editor = "Riccardo Barbieri",
booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Ismail, H, Radwan, I, Suominen, H & Goecke, R 2019, Gait Estimation and Analysis from Noisy Observations. in R Barbieri (ed.), 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, Institute of Electrical and Electronics Engineers, pp. 2707-2712, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 23/07/19. https://doi.org/10.1109/EMBC.2019.8857156

Gait Estimation and Analysis from Noisy Observations. / Ismail, Hafsa; Radwan, Ibrahim; Suominen, Hanna; Goecke, Roland.

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). ed. / Riccardo Barbieri. IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 2707-2712.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Gait Estimation and Analysis from Noisy Observations

AU - Ismail, Hafsa

AU - Radwan, Ibrahim

AU - Suominen, Hanna

AU - Goecke, Roland

PY - 2019

Y1 - 2019

N2 - People’s walking style – their gait – can be an indicator of their health as it is affected by pain, illness, weakness, and aging. Gait analysis aims to detect gait variations. It is usually performed by an experienced observer with the help of different devices, such as cameras, sensors, and/or force plates. Frequent gait analysis, to observe changes over time, is costly and impractical. This paper initiates an inexpensive gait analysis based on recorded video. Our methodology first discusses estimating gait movements from predicted 2D joint locations that represent selected body parts from videos. Then, using a long-short-term memory (LSTM) regression model to predict 3D (Vicon) data, which was recorded simultaneously with the videos as ground truth. Feet movements estimated from video are highly correlated with the Vicon data, enabling gait analysis by measuring selected spatial gait parameters (step and cadence length, and walk base) from estimated movements. Using inexpensive and reliable cameras to record, estimate and analyse a person’s gait can be helpful; early detection of its changes facilitates early intervention.

AB - People’s walking style – their gait – can be an indicator of their health as it is affected by pain, illness, weakness, and aging. Gait analysis aims to detect gait variations. It is usually performed by an experienced observer with the help of different devices, such as cameras, sensors, and/or force plates. Frequent gait analysis, to observe changes over time, is costly and impractical. This paper initiates an inexpensive gait analysis based on recorded video. Our methodology first discusses estimating gait movements from predicted 2D joint locations that represent selected body parts from videos. Then, using a long-short-term memory (LSTM) regression model to predict 3D (Vicon) data, which was recorded simultaneously with the videos as ground truth. Feet movements estimated from video are highly correlated with the Vicon data, enabling gait analysis by measuring selected spatial gait parameters (step and cadence length, and walk base) from estimated movements. Using inexpensive and reliable cameras to record, estimate and analyse a person’s gait can be helpful; early detection of its changes facilitates early intervention.

KW - Human gait

KW - Long Short-Term Memory

UR - http://www.mendeley.com/research/gait-estimation-analysis-noisy-observations

U2 - 10.1109/EMBC.2019.8857156

DO - 10.1109/EMBC.2019.8857156

M3 - Conference contribution

SN - 9781538613122

SP - 2707

EP - 2712

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

A2 - Barbieri, Riccardo

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Ismail H, Radwan I, Suominen H, Goecke R. Gait Estimation and Analysis from Noisy Observations. In Barbieri R, editor, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 2707-2712 https://doi.org/10.1109/EMBC.2019.8857156