Recognition of Abnormal Human Behavior in Elevators based on CNN

Yajing Shi; Benjun Guo; Yuanping Xu; Zhijie Xu; Jian Huang; Jun Lu; Dengguo Yao

doi:10.23919/ICAC50006.2021.9594189

Recognition of Abnormal Human Behavior in Elevators based on CNN

Yajing Shi, Benjun Guo, Yuanping Xu, Zhijie Xu, Jian Huang, Jun Lu, Dengguo Yao

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

4 Citations (Scopus)

Abstract

This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN (S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior.

Original language	English
Title of host publication	2021 26th International Conference on Automation and Computing
Subtitle of host publication	System Intelligence through Automation and Computing, ICAC 2021
Editors	Chenguang Yang
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781860435577
ISBN (Print)	9781665443524
DOIs	https://doi.org/10.23919/ICAC50006.2021.9594189
Publication status	Published - 15 Nov 2021
Event	26th International Conference on Automation and Computing - University of Portsmouth, Portsmouth, United Kingdom Duration: 2 Sep 2021 → 4 Sep 2021 Conference number: 26 http://www.cacsuk.co.uk/index.php/icac2021 https://www.ieee-ras.org/conferences-workshops/technically-co-sponsored/icac https://ieeexplore.ieee.org/xpl/conhome/9594055/proceeding

Conference

Conference	26th International Conference on Automation and Computing
Abbreviated title	ICAC 2021
Country/Territory	United Kingdom
City	Portsmouth
Period	2/09/21 → 4/09/21
Internet address	http://www.cacsuk.co.uk/index.php/icac2021 https://www.ieee-ras.org/conferences-workshops/technically-co-sponsored/icac https://ieeexplore.ieee.org/xpl/conhome/9594055/proceeding

UN SDGs

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

Access to Document

10.23919/ICAC50006.2021.9594189Licence: Unspecified

Cite this

@inproceedings{8f52044341aa498f887491e2ee84b5a7,

title = "Recognition of Abnormal Human Behavior in Elevators based on CNN",

abstract = "This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN (S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior. ",

keywords = "Abnormal behavior, CNN, Door blocking, Door picking, Elevator cabs",

author = "Yajing Shi and Benjun Guo and Yuanping Xu and Zhijie Xu and Jian Huang and Jun Lu and Dengguo Yao",

note = "Funding Information: This work is supported by the NSFC (61203172), the Sichuan Science and Technology Programs (2019YFH0187 and 2020018). Publisher Copyright: {\textcopyright} 2021 Chinese Automation and Computing Society in the UK-CACSUK.; 26th International Conference on Automation and Computing, ICAC 2021 ; Conference date: 02-09-2021 Through 04-09-2021",

year = "2021",

month = nov,

day = "15",

doi = "10.23919/ICAC50006.2021.9594189",

language = "English",

isbn = "9781665443524",

editor = "Chenguang Yang",

booktitle = "2021 26th International Conference on Automation and Computing",

publisher = "IEEE",

address = "United States",

url = "http://www.cacsuk.co.uk/index.php/icac2021, https://www.ieee-ras.org/conferences-workshops/technically-co-sponsored/icac, https://ieeexplore.ieee.org/xpl/conhome/9594055/proceeding",

}

Shi, Y, Guo, B, Xu, Y, Xu, Z, Huang, J, Lu, J & Yao, D 2021, Recognition of Abnormal Human Behavior in Elevators based on CNN. in C Yang (ed.), 2021 26th International Conference on Automation and Computing: System Intelligence through Automation and Computing, ICAC 2021., 9594189, IEEE, 26th International Conference on Automation and Computing, Portsmouth, United Kingdom, 2/09/21. https://doi.org/10.23919/ICAC50006.2021.9594189

Recognition of Abnormal Human Behavior in Elevators based on CNN. / Shi, Yajing; Guo, Benjun; Xu, Yuanping et al.

2021 26th International Conference on Automation and Computing: System Intelligence through Automation and Computing, ICAC 2021. ed. / Chenguang Yang. IEEE, 2021. 9594189.

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

TY - GEN

T1 - Recognition of Abnormal Human Behavior in Elevators based on CNN

AU - Shi, Yajing

AU - Guo, Benjun

AU - Xu, Yuanping

AU - Xu, Zhijie

AU - Huang, Jian

AU - Lu, Jun

AU - Yao, Dengguo

N1 - Conference code: 26

PY - 2021/11/15

Y1 - 2021/11/15

N2 - This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN (S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior.

AB - This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN (S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior.

KW - Abnormal behavior

KW - CNN

KW - Door blocking

KW - Door picking

KW - Elevator cabs

UR - http://www.scopus.com/inward/record.url?scp=85123209200&partnerID=8YFLogxK

U2 - 10.23919/ICAC50006.2021.9594189

DO - 10.23919/ICAC50006.2021.9594189

M3 - Conference contribution

AN - SCOPUS:85123209200

SN - 9781665443524

BT - 2021 26th International Conference on Automation and Computing

A2 - Yang, Chenguang

PB - IEEE

T2 - 26th International Conference on Automation and Computing

Y2 - 2 September 2021 through 4 September 2021

ER -

Recognition of Abnormal Human Behavior in Elevators based on CNN

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this