Vision-based fall detection through shape features

Chih Yang Lin; Shang Ming Wang; Jia Wei Hong; Li Wei Kang; Chung Lin Huang

doi:10.1109/BigMM.2016.22

Vision-based fall detection through shape features

Chih Yang Lin, Shang Ming Wang, Jia Wei Hong, Li Wei Kang, Chung Lin Huang

研究成果: 書貢獻/報告類型 › 會議論文篇章

20 引文斯高帕斯（Scopus）

摘要

A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before motion history image (MHI) is applied to analyze the fall behavior. Finally, two extra features, acceleration and angular acceleration, are proposed to more accurately determine whether a fall event has happened.

原文	英語
主出版物標題	Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	237-240
頁數	4
ISBN（電子）	9781509021789
DOIs	https://doi.org/10.1109/BigMM.2016.22
出版狀態	已發佈 - 2016 8月 16
對外發佈	是
事件	2nd IEEE International Conference on Multimedia Big Data, BigMM 2016 - Taipei, 臺灣持續時間: 2016 4月 20 → 2016 4月 22

出版系列

名字	Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

會議

會議	2nd IEEE International Conference on Multimedia Big Data, BigMM 2016
國家/地區	臺灣
城市	Taipei
期間	2016/04/20 → 2016/04/22

ASJC Scopus subject areas

訊號處理
資訊系統
媒體技術

存取文件

10.1109/BigMM.2016.22

其它文件與鏈接

Link to publication in Scopus

引用此

Lin, C. Y., Wang, S. M., Hong, J. W., Kang, L. W., & Huang, C. L. (2016). Vision-based fall detection through shape features. 於 Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016 (頁 237-240). 文章 7545029 (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigMM.2016.22

Vision-based fall detection through shape features. / Lin, Chih Yang; Wang, Shang Ming; Hong, Jia Wei 等.
Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 237-240 7545029 (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016).

研究成果: 書貢獻/報告類型 › 會議論文篇章

Lin, CY, Wang, SM, Hong, JW, Kang, LW & Huang, CL 2016, Vision-based fall detection through shape features. 於 Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016., 7545029, Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016, Institute of Electrical and Electronics Engineers Inc., 頁 237-240, 2nd IEEE International Conference on Multimedia Big Data, BigMM 2016, Taipei, 臺灣, 2016/04/20. https://doi.org/10.1109/BigMM.2016.22

Lin CY, Wang SM, Hong JW, Kang LW, Huang CL. Vision-based fall detection through shape features. 於 Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 237-240. 7545029. (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016). doi: 10.1109/BigMM.2016.22

@inproceedings{f1ae8d9404c44e1cbe6e5bc03fa0e6bb,

title = "Vision-based fall detection through shape features",

abstract = "A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before motion history image (MHI) is applied to analyze the fall behavior. Finally, two extra features, acceleration and angular acceleration, are proposed to more accurately determine whether a fall event has happened.",

keywords = "Fall detection, Motion features, Motion history image",

author = "Lin, {Chih Yang} and Wang, {Shang Ming} and Hong, {Jia Wei} and Kang, {Li Wei} and Huang, {Chung Lin}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2nd IEEE International Conference on Multimedia Big Data, BigMM 2016 ; Conference date: 20-04-2016 Through 22-04-2016",

year = "2016",

month = aug,

day = "16",

doi = "10.1109/BigMM.2016.22",

language = "English",

series = "Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016",

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

pages = "237--240",

booktitle = "Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016",

}

TY - GEN

T1 - Vision-based fall detection through shape features

AU - Lin, Chih Yang

AU - Wang, Shang Ming

AU - Hong, Jia Wei

AU - Kang, Li Wei

AU - Huang, Chung Lin

PY - 2016/8/16

Y1 - 2016/8/16

N2 - A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before motion history image (MHI) is applied to analyze the fall behavior. Finally, two extra features, acceleration and angular acceleration, are proposed to more accurately determine whether a fall event has happened.

AB - A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before motion history image (MHI) is applied to analyze the fall behavior. Finally, two extra features, acceleration and angular acceleration, are proposed to more accurately determine whether a fall event has happened.

KW - Fall detection

KW - Motion features

KW - Motion history image

UR - http://www.scopus.com/inward/record.url?scp=84987606983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987606983&partnerID=8YFLogxK

U2 - 10.1109/BigMM.2016.22

DO - 10.1109/BigMM.2016.22

M3 - Conference contribution

AN - SCOPUS:84987606983

T3 - Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

SP - 237

EP - 240

BT - Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Conference on Multimedia Big Data, BigMM 2016

Y2 - 20 April 2016 through 22 April 2016

ER -

Vision-based fall detection through shape features

摘要

出版系列

會議

ASJC Scopus subject areas

存取文件

其它文件與鏈接

指紋

引用此