Video-based real-time fall detection method in complex background

Kaizheng Chen; Yaping Dai; Yan Zhang; Zhiyang Jia; Kaoru Hirota

Video-based real-time fall detection method in complex background

Kaizheng Chen, Yaping Dai, Yan Zhang, Zhiyang Jia^*, Kaoru Hirota

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Contribution to conference › Paper › peer-review

Abstract

In order to solve the problem of real time detection of elderly fall in complex background, a video-based real-time fall detection method is proposed. The method consists of moving target detection, moving target box selection, moving target fall detection and warning system. The Gaussian Mixture Model and Hue,Saturation and Value(HSV) space shadow removal algorithm are used to extract the foreground for moving target detection. For moving target box selection, a box selection based on quadratic contour detection method is proposed to solve the problem of serious foreground fragmentation in complex background. The moving target fall detection is accomplished with support vector machine, by experiment, the accuracy is 96.86%. The key frame technology is used to satisfy the real-time detection requirement. Combined with Telnet technology, the function of email warning is achieved.

Original language	English
Publication status	Published - 2018
Event	8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018 - Tengzhou, Shandong, China Duration: 2 Nov 2018 → 6 Nov 2018

Conference

Conference	8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018
Country/Territory	China
City	Tengzhou, Shandong
Period	2/11/18 → 6/11/18

Keywords

Complex Background Image Processing
Fall Detection
Real-time Detection
Video Surveillance

Cite this

Chen, K., Dai, Y., Zhang, Y., Jia, Z., & Hirota, K. (2018). Video-based real-time fall detection method in complex background. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

@conference{c159ba640eaf43db8ebe706e956ab195,

title = "Video-based real-time fall detection method in complex background",

abstract = "In order to solve the problem of real time detection of elderly fall in complex background, a video-based real-time fall detection method is proposed. The method consists of moving target detection, moving target box selection, moving target fall detection and warning system. The Gaussian Mixture Model and Hue,Saturation and Value(HSV) space shadow removal algorithm are used to extract the foreground for moving target detection. For moving target box selection, a box selection based on quadratic contour detection method is proposed to solve the problem of serious foreground fragmentation in complex background. The moving target fall detection is accomplished with support vector machine, by experiment, the accuracy is 96.86%. The key frame technology is used to satisfy the real-time detection requirement. Combined with Telnet technology, the function of email warning is achieved.",

keywords = "Complex Background Image Processing, Fall Detection, Real-time Detection, Video Surveillance",

author = "Kaizheng Chen and Yaping Dai and Yan Zhang and Zhiyang Jia and Kaoru Hirota",

note = "Publisher Copyright: {\textcopyright} ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Application.; 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018 ; Conference date: 02-11-2018 Through 06-11-2018",

year = "2018",

language = "English",

}

Chen, K, Dai, Y, Zhang, Y, Jia, Z & Hirota, K 2018, 'Video-based real-time fall detection method in complex background', Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China, 2/11/18 - 6/11/18.

Video-based real-time fall detection method in complex background. / Chen, Kaizheng; Dai, Yaping; Zhang, Yan et al.
2018. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Video-based real-time fall detection method in complex background

AU - Chen, Kaizheng

AU - Dai, Yaping

AU - Zhang, Yan

AU - Jia, Zhiyang

AU - Hirota, Kaoru

N1 - Publisher Copyright: © ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Application.

PY - 2018

Y1 - 2018

N2 - In order to solve the problem of real time detection of elderly fall in complex background, a video-based real-time fall detection method is proposed. The method consists of moving target detection, moving target box selection, moving target fall detection and warning system. The Gaussian Mixture Model and Hue,Saturation and Value(HSV) space shadow removal algorithm are used to extract the foreground for moving target detection. For moving target box selection, a box selection based on quadratic contour detection method is proposed to solve the problem of serious foreground fragmentation in complex background. The moving target fall detection is accomplished with support vector machine, by experiment, the accuracy is 96.86%. The key frame technology is used to satisfy the real-time detection requirement. Combined with Telnet technology, the function of email warning is achieved.

AB - In order to solve the problem of real time detection of elderly fall in complex background, a video-based real-time fall detection method is proposed. The method consists of moving target detection, moving target box selection, moving target fall detection and warning system. The Gaussian Mixture Model and Hue,Saturation and Value(HSV) space shadow removal algorithm are used to extract the foreground for moving target detection. For moving target box selection, a box selection based on quadratic contour detection method is proposed to solve the problem of serious foreground fragmentation in complex background. The moving target fall detection is accomplished with support vector machine, by experiment, the accuracy is 96.86%. The key frame technology is used to satisfy the real-time detection requirement. Combined with Telnet technology, the function of email warning is achieved.

KW - Complex Background Image Processing

KW - Fall Detection

KW - Real-time Detection

KW - Video Surveillance

UR - http://www.scopus.com/inward/record.url?scp=85057974428&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85057974428

T2 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018

Y2 - 2 November 2018 through 6 November 2018

ER -

Video-based real-time fall detection method in complex background

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this