Kinect-based non-intrusive human gait analysis and visualization

Nguyen-Luc  Dao; Yuzhe  Zhang; Jianmin Zheng; Jianfei Cai

doi:10.1109/MMSP.2015.7340804

Kinect-based non-intrusive human gait analysis and visualization

Nguyen-Luc Dao
, Yuzhe Zhang
, Jianmin Zheng
, Jianfei Cai

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

7 Citations (Scopus)

Abstract

Home healthcare becomes more and more important with the increased aging population. The advent of various low-cost sensing devices makes it tempting to develop low-cost, non-intrusive systems to monitor the variations of human being. In this paper, we describe a Kinect-based gait analysis and visualization system as a case study in this direction. The system uses depth images and skeleton captured by the Kinect to generate a BVH file recording the motion information, extracts features of gait for detecting abnormal gait, and customizes the 3D body model for personalized motion visualization. Compared to previous work in this area, the proposed system has advantages since it integrates gait classification and visualization which may bring new possibilities in healthcare. The experiments show that our proposed system achieves accurate gait classification as well as flexible personalized 3D visualization.

Original language	English
Title of host publication	2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China
Editors	Tao Mei , Gene Cheung
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	90-95
Number of pages	6
ISBN (Electronic)	9781467374781, 9781467374774
DOIs	https://doi.org/10.1109/MMSP.2015.7340804
Publication status	Published - 2015
Externally published	Yes
Event	IEEE International Workshop on Multimedia Signal Processing 2015 - Xiamen, China Duration: 19 Oct 2015 → 21 Oct 2015 Conference number: 17th https://web.archive.org/web/20160401143159/http://www.mmsp2015.org/index.html https://ieeexplore.ieee.org/xpl/conhome/7331772/proceeding (Proceedings)

Conference

Conference	IEEE International Workshop on Multimedia Signal Processing 2015
Abbreviated title	MMSP 2015
Country/Territory	China
City	Xiamen
Period	19/10/15 → 21/10/15
Internet address	https://web.archive.org/web/20160401143159/http://www.mmsp2015.org/index.html https://ieeexplore.ieee.org/xpl/conhome/7331772/proceeding (Proceedings)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Data visualization
Feature extraction
Foot
Knee
Medical services
Skeleton
Three-dimensional displays

Access to Document

10.1109/MMSP.2015.7340804

Cite this

Dao, N.-L., Zhang, Y., Zheng, J., & Cai, J. (2015). Kinect-based non-intrusive human gait analysis and visualization. In T. Mei , & G. Cheung (Eds.), 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China (pp. 90-95). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/MMSP.2015.7340804

@inproceedings{db8a673500d7443dac67d59ccdccaf29,

title = "Kinect-based non-intrusive human gait analysis and visualization",

abstract = "Home healthcare becomes more and more important with the increased aging population. The advent of various low-cost sensing devices makes it tempting to develop low-cost, non-intrusive systems to monitor the variations of human being. In this paper, we describe a Kinect-based gait analysis and visualization system as a case study in this direction. The system uses depth images and skeleton captured by the Kinect to generate a BVH file recording the motion information, extracts features of gait for detecting abnormal gait, and customizes the 3D body model for personalized motion visualization. Compared to previous work in this area, the proposed system has advantages since it integrates gait classification and visualization which may bring new possibilities in healthcare. The experiments show that our proposed system achieves accurate gait classification as well as flexible personalized 3D visualization.",

keywords = "Data visualization, Feature extraction, Foot, Knee, Medical services, Skeleton, Three-dimensional displays",

author = "Nguyen-Luc Dao and Yuzhe Zhang and Jianmin Zheng and Jianfei Cai",

year = "2015",

doi = "10.1109/MMSP.2015.7340804",

language = "English",

pages = "90--95",

editor = "\{Mei \}, \{Tao \} and \{Cheung \}, Gene",

booktitle = "2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Workshop on Multimedia Signal Processing 2015, MMSP 2015 ; Conference date: 19-10-2015 Through 21-10-2015",

url = "https://web.archive.org/web/20160401143159/http://www.mmsp2015.org/index.html, https://ieeexplore.ieee.org/xpl/conhome/7331772/proceeding",

}

Dao, N-L, Zhang, Y, Zheng, J & Cai, J 2015, Kinect-based non-intrusive human gait analysis and visualization. in T Mei & G Cheung (eds), 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 90-95, IEEE International Workshop on Multimedia Signal Processing 2015, Xiamen, China, 19/10/15. https://doi.org/10.1109/MMSP.2015.7340804

Kinect-based non-intrusive human gait analysis and visualization. / Dao, Nguyen-Luc ; Zhang, Yuzhe ; Zheng, Jianmin et al.
2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China. ed. / Tao Mei ; Gene Cheung . Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 90-95.

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

TY - GEN

T1 - Kinect-based non-intrusive human gait analysis and visualization

AU - Dao, Nguyen-Luc

AU - Zhang, Yuzhe

AU - Zheng, Jianmin

AU - Cai, Jianfei

N1 - Conference code: 17th

PY - 2015

Y1 - 2015

N2 - Home healthcare becomes more and more important with the increased aging population. The advent of various low-cost sensing devices makes it tempting to develop low-cost, non-intrusive systems to monitor the variations of human being. In this paper, we describe a Kinect-based gait analysis and visualization system as a case study in this direction. The system uses depth images and skeleton captured by the Kinect to generate a BVH file recording the motion information, extracts features of gait for detecting abnormal gait, and customizes the 3D body model for personalized motion visualization. Compared to previous work in this area, the proposed system has advantages since it integrates gait classification and visualization which may bring new possibilities in healthcare. The experiments show that our proposed system achieves accurate gait classification as well as flexible personalized 3D visualization.

AB - Home healthcare becomes more and more important with the increased aging population. The advent of various low-cost sensing devices makes it tempting to develop low-cost, non-intrusive systems to monitor the variations of human being. In this paper, we describe a Kinect-based gait analysis and visualization system as a case study in this direction. The system uses depth images and skeleton captured by the Kinect to generate a BVH file recording the motion information, extracts features of gait for detecting abnormal gait, and customizes the 3D body model for personalized motion visualization. Compared to previous work in this area, the proposed system has advantages since it integrates gait classification and visualization which may bring new possibilities in healthcare. The experiments show that our proposed system achieves accurate gait classification as well as flexible personalized 3D visualization.

KW - Data visualization

KW - Feature extraction

KW - Foot

KW - Knee

KW - Medical services

KW - Skeleton

KW - Three-dimensional displays

UR - https://www.scopus.com/pages/publications/84960459305

U2 - 10.1109/MMSP.2015.7340804

DO - 10.1109/MMSP.2015.7340804

M3 - Conference Paper

AN - SCOPUS:84960459305

SP - 90

EP - 95

BT - 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) - October 19-21 2015, Xiamen, China

A2 - Mei , Tao

A2 - Cheung , Gene

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Workshop on Multimedia Signal Processing 2015

Y2 - 19 October 2015 through 21 October 2015

ER -

Kinect-based non-intrusive human gait analysis and visualization

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Cite this