Improving the Accuracy of Gait Detection Using Computer Vision

Sota Sugiyama; Yuna Ogiso; Masataka Yamamoto; Yuto Ishige; Hiroshi Takemura; Naoyuki Aikawa

doi:10.1109/TENSYMP55890.2023.10223625

Improving the Accuracy of Gait Detection Using Computer Vision

Sota Sugiyama, Yuna Ogiso, Masataka Yamamoto, Yuto Ishige, Hiroshi Takemura, Naoyuki Aikawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Using computer vision for gait analysis is easier and more cost-effective to implement in the field than using wearable devices or motion capture, etc. OpenPose is one of the freely available skeletal detection algorithms, but the accuracy of skeletal detection is not always high. Therefore, in this paper, the gait cycle is derived from the skeletal coordinate data obtained by general OpenPose. Based on the gait cycle, we propose a method to predict the coordinates and correct the skeletal coordinates.

Original language	English
Title of host publication	2023 IEEE Region 10 Symposium, TENSYMP 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665482585
DOIs	https://doi.org/10.1109/TENSYMP55890.2023.10223625
Publication status	Published - 2023
Event	2023 IEEE Region 10 Symposium, TENSYMP 2023 - Canberra, Australia Duration: 6 Sept 2023 → 8 Sept 2023

Publication series

Name	2023 IEEE Region 10 Symposium, TENSYMP 2023

Conference

Conference	2023 IEEE Region 10 Symposium, TENSYMP 2023
Country/Territory	Australia
City	Canberra
Period	6/09/23 → 8/09/23

Keywords

Gait Analysis
OpenPose
Skeleton Detection
Video Processing

Access to Document

10.1109/TENSYMP55890.2023.10223625

Cite this

@inproceedings{ec184bd740db4bb089d04d79ed984655,

title = "Improving the Accuracy of Gait Detection Using Computer Vision",

abstract = "Using computer vision for gait analysis is easier and more cost-effective to implement in the field than using wearable devices or motion capture, etc. OpenPose is one of the freely available skeletal detection algorithms, but the accuracy of skeletal detection is not always high. Therefore, in this paper, the gait cycle is derived from the skeletal coordinate data obtained by general OpenPose. Based on the gait cycle, we propose a method to predict the coordinates and correct the skeletal coordinates.",

keywords = "Gait Analysis, OpenPose, Skeleton Detection, Video Processing",

author = "Sota Sugiyama and Yuna Ogiso and Masataka Yamamoto and Yuto Ishige and Hiroshi Takemura and Naoyuki Aikawa",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Region 10 Symposium, TENSYMP 2023 ; Conference date: 06-09-2023 Through 08-09-2023",

year = "2023",

doi = "10.1109/TENSYMP55890.2023.10223625",

language = "English",

series = "2023 IEEE Region 10 Symposium, TENSYMP 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE Region 10 Symposium, TENSYMP 2023",

}

Sugiyama, S, Ogiso, Y, Yamamoto, M, Ishige, Y, Takemura, H & Aikawa, N 2023, Improving the Accuracy of Gait Detection Using Computer Vision. in 2023 IEEE Region 10 Symposium, TENSYMP 2023. 2023 IEEE Region 10 Symposium, TENSYMP 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Region 10 Symposium, TENSYMP 2023, Canberra, Australia, 6/09/23. https://doi.org/10.1109/TENSYMP55890.2023.10223625

Improving the Accuracy of Gait Detection Using Computer Vision. / Sugiyama, Sota; Ogiso, Yuna; Yamamoto, Masataka et al.
2023 IEEE Region 10 Symposium, TENSYMP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Region 10 Symposium, TENSYMP 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improving the Accuracy of Gait Detection Using Computer Vision

AU - Sugiyama, Sota

AU - Ogiso, Yuna

AU - Yamamoto, Masataka

AU - Ishige, Yuto

AU - Takemura, Hiroshi

AU - Aikawa, Naoyuki

PY - 2023

Y1 - 2023

N2 - Using computer vision for gait analysis is easier and more cost-effective to implement in the field than using wearable devices or motion capture, etc. OpenPose is one of the freely available skeletal detection algorithms, but the accuracy of skeletal detection is not always high. Therefore, in this paper, the gait cycle is derived from the skeletal coordinate data obtained by general OpenPose. Based on the gait cycle, we propose a method to predict the coordinates and correct the skeletal coordinates.

AB - Using computer vision for gait analysis is easier and more cost-effective to implement in the field than using wearable devices or motion capture, etc. OpenPose is one of the freely available skeletal detection algorithms, but the accuracy of skeletal detection is not always high. Therefore, in this paper, the gait cycle is derived from the skeletal coordinate data obtained by general OpenPose. Based on the gait cycle, we propose a method to predict the coordinates and correct the skeletal coordinates.

KW - Gait Analysis

KW - OpenPose

KW - Skeleton Detection

KW - Video Processing

UR - http://www.scopus.com/inward/record.url?scp=85173526953&partnerID=8YFLogxK

U2 - 10.1109/TENSYMP55890.2023.10223625

DO - 10.1109/TENSYMP55890.2023.10223625

M3 - Conference contribution

AN - SCOPUS:85173526953

T3 - 2023 IEEE Region 10 Symposium, TENSYMP 2023

BT - 2023 IEEE Region 10 Symposium, TENSYMP 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Region 10 Symposium, TENSYMP 2023

Y2 - 6 September 2023 through 8 September 2023

ER -

Improving the Accuracy of Gait Detection Using Computer Vision

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this