Real-time crowd counting via mobile-friendly Vision Transformer network

Peirong Ji; Zhiwei Wu; Yan Chen; Mohammad S. Alam; Jun Sang

doi:10.1117/12.2663761

13 June 2023 Real-time crowd counting via mobile-friendly Vision Transformer network

Peirong Ji, Zhiwei Wu, Yan Chen, Mohammad S. Alam, Jun Sang

Author Affiliations +

Proceedings Volume 12527, Pattern Recognition and Tracking XXXIV; 125270U (2023) https://doi.org/10.1117/12.2663761
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Conference Poster

Abstract

Accurate crowd counting in congested scenes remain challengeable in the trade-off of efficiency and generalization. For solving this issue, we propose a mobile-friendly solution for the network deployment in high response speed demand scenarios. In order to introduce the profound potential of global crowd representations to lightweight counting model, this work suggests a novel crowd counting aimed mobile vision transformers architecture (CCMTNet), which strives for enhancing the efficiency of the model universality in real-time crowd counting tasks on resource constrained computing devices. The framework of linear CNN network interpolation structure with self-attention blocks endows the model with the ability of local feature extraction and global high-dimensional crowd information processing with low computational cost. In addition, several experimental networks with different scales based on the proposed architecture are comprehensively verified to balance the accuracy loss as compressing the computing costs. Extensive experiments on three mainstream datasets for crowd counting tasks well demonstrate the effectiveness of this proposed network. Particularly, CCMTNet achieves the feasibility of reconciling the counting accuracy and efficiency in comparisons with traditional lightweight CNN networks.

Citation Download Citation

Peirong Ji, Zhiwei Wu, Yan Chen, Mohammad S. Alam, and Jun Sang "Real-time crowd counting via mobile-friendly Vision Transformer network", Proc. SPIE 12527, Pattern Recognition and Tracking XXXIV, 125270U (13 June 2023); https://doi.org/10.1117/12.2663761

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