ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2024-09-04 15:30
The Research on Dangerous Behavior Recognition and Warning System for Escalators Based on Deep Learning Models
YongXuan Zhu, Hiroyuki Nakamura (S.I.T)
Abstract (in Japanese) (See Japanese page) 
(in English) In this study, we developed a system that uses deep learning and image recognition technology to identify potential dangerous behaviors on escalators in real-time and issue voice warnings. The system aims to accurately detect actions that are the main causes of escalator accidents, such as moving in the wrong direction, stepping over the yellow line, and bringing large luggage, and to immediately issue warnings. The system extracts frames from real-time video streams, generates high-precision data using skeleton keypoint extraction with OpenPose and YOLO v8 technology. Based on the detected dangerous behaviors, automatic voice warnings are issued, contributing to the improvement of escalator user safety and the prevention of accidents.
Keyword (in Japanese) (See Japanese page) 
(in English) Escalator / Deep Learning / Image Recognition / YOLO v8 / Keras / / /  
Reference Info. ITE Tech. Rep., vol. 48, no. 29, ME2024-80, pp. 1-5, Sept. 2024.
Paper # ME2024-80 
Date of Issue 2024-08-28 (ME) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee ME IEICE-EMM IEICE-IE IEICE-LOIS IEE-CMN IPSJ-AVM  
Conference Date 2024-09-04 - 2024-09-05 
Place (in Japanese) (See Japanese page) 
Place (in English) Hiroshima Institute of Technology 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To ME 
Conference Code 2024-09-ME-EMM-IE-LOIS-CMN-AVM 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) The Research on Dangerous Behavior Recognition and Warning System for Escalators Based on Deep Learning Models 
Sub Title (in English)  
Keyword(1) Escalator  
Keyword(2) Deep Learning  
Keyword(3) Image Recognition  
Keyword(4) YOLO v8  
Keyword(5) Keras  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name YongXuan Zhu  
1st Author's Affiliation Shibaura Institute of Technology (S.I.T)
2nd Author's Name Hiroyuki Nakamura  
2nd Author's Affiliation Shibaura Institute of Technology (S.I.T)
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2024-09-04 15:30:00 
Presentation Time 20 minutes 
Registration for ME 
Paper # ME2024-80 
Volume (vol) vol.48 
Number (no) no.29 
Page pp.1-5 
#Pages
Date of Issue 2024-08-28 (ME) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan