skip to main content
10.1145/3445815.3445841acmotherconferencesArticle/Chapter ViewAbstractPublication PagescsaiConference Proceedingsconference-collections
research-article

Two-stream Adaptive Convolutional Neural Network for Crowd Counting

Published: 17 March 2021 Publication History

Abstract

Due to the high crowd density in some scenes and the large differences in crowd feature scales, it is difficult to count the number of people. The structure of the multi-branch CNN can deal with the features of different scales, improve the accuracy of crowd counting, but also increase the parameters and become more complicated. In this paper, a 2S-ACNN with a simple structure and balanced performance is proposed for crowd counting in a single frame image. The network structure uses different sizes of receptive field to deal with features of different scales, and adds a multi-scale pooling structure to carry out feature fusion, which improve the representation ability of the model. The experimental results show that this method can maintain fewer parameters and achieve lower loss and higher accuracy.

References

[1]
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. 1998. Gradient based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324
[2]
Navneet, D., Triggs, B. 2005. Histogram of oriented gradients for human detection. IN CVPR
[3]
Viola, p., Jones, M. 2004. Robust real-time face detection. International journal of computer vision
[4]
Cortes, Vapnik, V. 1995. Support vector netwos. Machine Learning
[5]
Yoav Freund, Robert E Schapire. 1997. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting[J]. Journal of Computer and System Sciences, 55(1):119-139.
[6]
Girshick, R., Donahue, J., Darrell,T., 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. CVPR.
[7]
Ross Girshick. 2015. Fast R-CNN. ICCV.
[8]
Ren, S., He, K., Girshick, R., 2017. Faster r-cnn: towards real-time object detection with region proposal networks. Pattern Analysis Mach. Intell., (2017), 39, (6), pp. 1137–1149.
[9]
Redmon, J., Divvala, S., Girshick, R., 2016. You only look once: unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, (November 2016), pp. 779–788.
[10]
Liu, W., Anguelov, D., Erhan, D., 2016. Ssd: single shot multi box detector. Computer Vision ECCV, Amsterdam, Netherlands, (2016), pp. 21–37.
[11]
Nikos Paragios, Visvanathan Ramesh. 2006. A MRF-based Approach for Real-Time Subway Monitoring, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[12]
Chen, K., Loy, C., Gong, S., and Xiang, T. 2012. Feature mining for localised crowd counting. In BMVC, volume 1, page 3.
[13]
Chan, A.B., Liang, Z.S.J., and Vasconcelos, N. 2008. Privacy preserving crowd monitoring: Counting people without people models or tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1–7.
[14]
Viet-Quoc Pham, Tatsuo Kozakaya, Osamu Yamaguchi, Ryuzo Okada. 2015. count forest: co-voting uncertain number of targets using random forest for Crowd density estimation, ICCV.
[15]
Cong Zhang, Hongsheng Li, Xiaogang Wang, and Xiaokang Yang. 2015. Cross-scene Crowd Counting via Deep Convolutional Neural Networks, CVPR.
[16]
Yingying Zhang, Desen Zhou, Siqin Chen, 2016. Single-Image Crowd Counting via Multi-Column Convolutional Neural Network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016), pp. 589–597.
[17]
He K, Zhang X, Ren S, and Sun J. 2014. Spatial pyramid pooling in deep convolutional networks for visual recognition. ECCV, 346–361
[18]
Yanghao Li, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang. 2019. Scale-Aware Trident Networks for Object Detection, ICCV.
[19]
Ciregan, D., Meier, U., Schmidhuber, J. 2012. Multi-column deep neural networks for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[20]
Kingma, D. P., and Ba, J. 2015. Adam: Amethod for stochastic optimization, ICLR.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
CSAI '20: Proceedings of the 2020 4th International Conference on Computer Science and Artificial Intelligence
December 2020
294 pages
ISBN:9781450388436
DOI:10.1145/3445815
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 March 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Convolutional Neural Networks
  2. Crowd Counting
  3. Multi-scale
  4. Receptive Field

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

CSAI 2020

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 46
    Total Downloads
  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 25 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media