Deep learning-based fall detection

Jason Wei Hoe  Chiang; Li Zhang

doi:10.1142/9789811223334_0107

Deep learning-based fall detection

Jason Wei Hoe Chiang, Li Zhang

Computer and Information Sciences Department

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

9 Citations (Scopus)

59 Downloads (Pure)

Abstract

In the modern information era, fall accidents are one of the leading causes of injury, disability and death to elderly individuals. This research focuses on object detection and recognition using deep neural networks, which is applied to the theme of fall detection. We propose a deep learning algorithm with the capability to detect fall accidents based on the state-of-the-art object detector, YOLOv3. Our system is tested on a challenging video database with diverse fall accidents under different scenarios and achieves an overall accuracy rate of 63.33%. The proposed deep network shows great potential to be deployed in real-world scenarios for health monitoring.

Original language	English
Title of host publication	Developments of Artificial Intelligence Technologies in Computation and Robotics
Subtitle of host publication	Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020)
Editors	Zhong Li, Chunrong Yuan, Jie Lu, Etienne E. Kerre
Place of Publication	Singapore
Publisher	World Scientific
Pages	891-898
Number of pages	8
Volume	12
ISBN (Electronic)	9789811223341, 9789811223334
ISBN (Print)	9789811223327
DOIs	https://doi.org/10.1142/9789811223334_0107
Publication status	Published - Oct 2020
Event	The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020) - FernUniversitä t in Hagen/TH Köln, Cologne, Germany Duration: 18 Aug 2020 → 21 Aug 2020 https://www.hrm-bildung.de/flins2020/

Publication series

Name	World Scientific Proceedings Series on Computer Engineering and Information Science
Publisher	World Scientific
Volume	12
ISSN (Print)	1793-7868

Conference

Conference	The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020)
Country/Territory	Germany
City	Cologne
Period	18/08/20 → 21/08/20
Internet address	https://www.hrm-bildung.de/flins2020/

Keywords

Fall Detection
Deep Learning
Convolutional Neural Network

Access to Document

10.1142/9789811223334_0107

flins2020-falldetectionAccepted author manuscript, 643 KB

Cite this

Chiang, J. W. H., & Zhang, L. (2020). Deep learning-based fall detection. In Z. Li, C. Yuan, J. Lu, & E. E. Kerre (Eds.), Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020) (Vol. 12, pp. 891-898). (World Scientific Proceedings Series on Computer Engineering and Information Science; Vol. 12). World Scientific. https://doi.org/10.1142/9789811223334_0107

Chiang, Jason Wei Hoe ; Zhang, Li. / Deep learning-based fall detection. Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020). editor / Zhong Li ; Chunrong Yuan ; Jie Lu ; Etienne E. Kerre. Vol. 12 Singapore : World Scientific, 2020. pp. 891-898 (World Scientific Proceedings Series on Computer Engineering and Information Science).

@inproceedings{8376e1a4fdeb459cad3fdf991c0c30ac,

title = "Deep learning-based fall detection",

abstract = "In the modern information era, fall accidents are one of the leading causes of injury, disability and death to elderly individuals. This research focuses on object detection and recognition using deep neural networks, which is applied to the theme of fall detection. We propose a deep learning algorithm with the capability to detect fall accidents based on the state-of-the-art object detector, YOLOv3. Our system is tested on a challenging video database with diverse fall accidents under different scenarios and achieves an overall accuracy rate of 63.33%. The proposed deep network shows great potential to be deployed in real-world scenarios for health monitoring.",

keywords = "Fall Detection, Deep Learning, Convolutional Neural Network",

author = "Chiang, {Jason Wei Hoe} and Li Zhang",

year = "2020",

month = oct,

doi = "10.1142/9789811223334_0107",

language = "English",

isbn = "9789811223327",

volume = "12",

series = "World Scientific Proceedings Series on Computer Engineering and Information Science",

publisher = "World Scientific",

pages = "891--898",

editor = "Zhong Li and Chunrong Yuan and Jie Lu and Kerre, {Etienne E.}",

booktitle = "Developments of Artificial Intelligence Technologies in Computation and Robotics",

address = "Singapore",

note = "The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020) ; Conference date: 18-08-2020 Through 21-08-2020",

url = "https://www.hrm-bildung.de/flins2020/",

}

Chiang, JWH & Zhang, L 2020, Deep learning-based fall detection. in Z Li, C Yuan, J Lu & EE Kerre (eds), Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020). vol. 12, World Scientific Proceedings Series on Computer Engineering and Information Science, vol. 12, World Scientific, Singapore, pp. 891-898, The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020), Cologne, Germany, 18/08/20. https://doi.org/10.1142/9789811223334_0107

Deep learning-based fall detection. / Chiang, Jason Wei Hoe ; Zhang, Li.
Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020). ed. / Zhong Li; Chunrong Yuan; Jie Lu; Etienne E. Kerre. Vol. 12 Singapore: World Scientific, 2020. p. 891-898 (World Scientific Proceedings Series on Computer Engineering and Information Science; Vol. 12).

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

TY - GEN

T1 - Deep learning-based fall detection

AU - Chiang, Jason Wei Hoe

AU - Zhang, Li

PY - 2020/10

Y1 - 2020/10

N2 - In the modern information era, fall accidents are one of the leading causes of injury, disability and death to elderly individuals. This research focuses on object detection and recognition using deep neural networks, which is applied to the theme of fall detection. We propose a deep learning algorithm with the capability to detect fall accidents based on the state-of-the-art object detector, YOLOv3. Our system is tested on a challenging video database with diverse fall accidents under different scenarios and achieves an overall accuracy rate of 63.33%. The proposed deep network shows great potential to be deployed in real-world scenarios for health monitoring.

AB - In the modern information era, fall accidents are one of the leading causes of injury, disability and death to elderly individuals. This research focuses on object detection and recognition using deep neural networks, which is applied to the theme of fall detection. We propose a deep learning algorithm with the capability to detect fall accidents based on the state-of-the-art object detector, YOLOv3. Our system is tested on a challenging video database with diverse fall accidents under different scenarios and achieves an overall accuracy rate of 63.33%. The proposed deep network shows great potential to be deployed in real-world scenarios for health monitoring.

KW - Fall Detection

KW - Deep Learning

KW - Convolutional Neural Network

UR - https://www.worldscientific.com/doi/abs/10.1142/9789811223334_0107

U2 - 10.1142/9789811223334_0107

DO - 10.1142/9789811223334_0107

M3 - Conference contribution

SN - 9789811223327

VL - 12

T3 - World Scientific Proceedings Series on Computer Engineering and Information Science

SP - 891

EP - 898

BT - Developments of Artificial Intelligence Technologies in Computation and Robotics

A2 - Li, Zhong

A2 - Yuan, Chunrong

A2 - Lu, Jie

A2 - Kerre, Etienne E.

PB - World Scientific

CY - Singapore

T2 - The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020)

Y2 - 18 August 2020 through 21 August 2020

ER -

Chiang JWH, Zhang L. Deep learning-based fall detection. In Li Z, Yuan C, Lu J, Kerre EE, editors, Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020). Vol. 12. Singapore: World Scientific. 2020. p. 891-898. (World Scientific Proceedings Series on Computer Engineering and Information Science). Epub 2020 Aug 13. doi: 10.1142/9789811223334_0107

Deep learning-based fall detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this