Multi-view branch-shared subway platform crowd counting method

Guoyan Liu; Jing Zuo

doi:10.1117/12.2668747

16 February 2023 Multi-view branch-shared subway platform crowd counting method

Guoyan Liu, Jing Zuo

Proceedings Volume 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022); 1259102 (2023) https://doi.org/10.1117/12.2668747
Event: 6th International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 2022, Guangzhou, China

Abstract

With the development of society, single-view crowd counting can no longer meet the existing social needs, in order to solve the existing problems, multi-view crowd counting emerged. The multi-view crowd counting is suitable for situations where a single view cannot cover the entire scene. In the rail transit industry, multi-view crowd counting can be used to count passengers on the platform, organize driving activity more scientifically and rationally, improve driving efficiency. In this paper, we propose a multi-view branch-shared crowd counting model for subway platforms, which uses a single branch to extract features and select scales for multi-perspective views. Compared with the existing multi-branch model, the structure of a single branch is more concise, and the feature redundancy is reduced. Considering the relationship between pixels, this paper introduces a combination of the local consistency loss function and Euclidean loss function. The performance of this model is tested on two public datasets (PETS2009 and CityStreet), and better results are obtained compared with the existing five methods.

Citation Download Citation

Guoyan Liu and Jing Zuo "Multi-view branch-shared subway platform crowd counting method", Proc. SPIE 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 1259102 (16 February 2023); https://doi.org/10.1117/12.2668747

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Convolution

Education and training

Cameras

Performance modeling

Data modeling

Matrices

Show All Keywords

Keywords/Phrases

Search In:

Publication Years