Analysis method of congestion degree of rail transit station platform

Jinshan Jian; Xiao Liang

doi:10.1117/12.2657859

22 December 2022 Analysis method of congestion degree of rail transit station platform

Jinshan Jian, Xiao Liang

Proceedings Volume 12460, International Conference on Smart Transportation and City Engineering (STCE 2022); 124600B (2022) https://doi.org/10.1117/12.2657859
Event: International Conference on Smart Transportation and City Engineering (STCE 2022), 2022, Chongqing, China

Abstract

In order to grasp the actual congestion level, travel safety and improve the management level of urban rail transit station, and study the analysis method of platform passenger congestion, this paper uses video technology to obtain the location distribution of passengers at Xi’dan station of Beijing Metro, and studies the distribution process and law of waiting passengers. Firstly, the individual and group behaviors of passengers on the platform are studied, and the actual distribution of passengers in a waiting period is selected to facilitate the division of the platform area; Based on the clustering analysis of density, Density-based clustering analysis (DBSCAN) algorithm can cluster the distribution data of passengers on the platform to realize the density division of the data set, which can effectively solve the clustering problem of the data set with uneven density distribution. Through the visualization of clustering results, it can reflect the aggregation and distribution characteristics of passenger group behavior to a certain extent.

Citation Download Citation

Jinshan Jian and Xiao Liang "Analysis method of congestion degree of rail transit station platform", Proc. SPIE 12460, International Conference on Smart Transportation and City Engineering (STCE 2022), 124600B (22 December 2022); https://doi.org/10.1117/12.2657859

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available