Journal of South China University of Technology(Natural Science) >

2020 , Vol. 48 >Issue 8: 10 - 21

DOI: https://doi.org/10.12141/j.issn.1000-565X.200010

Electronics, Communication & Automation Technology

Recognition of Passengers＇Abnormal Behavior on Escalator Based on Video Monitoring

Expand
  • 1． School of Automation Science and Engineering，South China University of Technology，Guangzhou 510640，Guangdong，China;2． Key Laboratory of Autonomous Systems and Network Control of the Ministry of Education，Guangzhou 510640，Guangdong，China;3． Guangzhou Metro Group Co．，Ltd．，Guangzhou 510335，Guangdong，China; 4． Hitachi Elevator (Guangzhou) Escalator Limited Liability Company，Guangzhou 510660，Guangdong，China
杜启亮(1980-)，男，博士，副研究员，主要从事机器人与机器视觉研究。

Received date: 2020-01-09

  Revised date: 2020-05-15

  Online published: 2020-05-22

Supported by

 Supported by the Coast Defence Public Welfare Project of the Ministry of Science and Technology of China(201505002)，the Science and Technology Planning Project of Guangdong Province (2016B090912001)，the Key Field R＆D Program “New Generation Artificial Intelligence”Major Science and Technology Project of Guangdong Province (2018B010109001) and the Key Field Ｒ＆D Program “Precision Agriculture”Key Special Project of Guangdong Province (2019B020214001)

Fold

Abstract

Aiming at the problem that dangerous behavior of passengers on the escalator is difficult to be accurately detected in real time，an algorithm for identifying abnormal behavior of escalator passengers based on video surveil-lance was proposed． Firstly，YOLOv3 was used to detect the position of the passenger in the image． Secondly，MobileNetv2 was used as the base network，which was combined with the deconvolution layer to extract the human skeleton of the detected passenger． Thirdly，the Hungarian assignment algorithm based on skeleton distance was used to realize the allocation of passenger ID numbers in the video． Finally，with keypoints as the input，the graph convolutional neural network was used to recognize the abnormal behavior of passenger． The experimental results on the GTX1080GPU show that the proposed recognition algorithm can achieve a processing speed of 15 f/s and an abnormal behavior recognition accuracy rate of 94. 3%，which can accurately recognize the abnormal behavior of passengers on the escalator in real time．

Key words： escalator; deep learning; convolutional neural networks; pedestrian detection; pose estimation; Hungarian assignment algorithm

Cite this article

DU Qiliang, HUANG Liguang, TIAN Lianfang, et al . Recognition of Passengers＇Abnormal Behavior on Escalator Based on Video Monitoring[J]. Journal of South China University of Technology(Natural Science), 2020 , 48(8) : 10 -21 . DOI: 10.12141/j.issn.1000-565X.200010

Options
Outlines

/

〈 〉