research-article

Crowd Counting using DMCNN

Authors:

Luyang WangAuthors Info & Claims

ICIAI '19: Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence

Pages 138 - 144

https://doi.org/10.1145/3319921.3319930

Published: 15 March 2019 Publication History

Abstract

To estimate the crowd density map and count the crowd from a single image accurately is always a challenging task. With arbitrary perspective and random crowd density, occlusions, appearance variations and perspective distortions may occur. Some of current crowd counting methods are based on image cropping. And some popular deep learning models are difficult to optimize. In this paper, we propose a Dilated Multi-column Convolutional Neural Network architecture for crowd density estimation in still images improved from the MCNN model [1]. We also use the dilated layer and optimize the loss function to get better accuracy. The DMCNN model is lightweight, easy to train and has better fitting ability. Meanwhile the architecture is an end-to-end system and robust for images with different perspective or crowd density. Furthermore, the ground truth (density map) is generated based on our Perspective-Adaptive Gaussian Kernels which can better represent the heads of pedestrians. We conduct experiments on the WorldExpo'10 dataset, the ShanghaiTech dataset, the UCF_CC_50 dataset, and the mall dataset. The results show that our method achieves better estimation and is convenient to utilize. Our DMCNN model has a good practical application prospect.

References

[1]

S. C. S. G. Y. Zhang, D. Zhou and Y. Ma, "Single image crowd counting via multi-column convolutional neural network," in IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 589--597.

[2]

I. K. K. M. L. C. Chen, G. Papandreou and A. L. Yuille, "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs," in IEEE Transactions on Pattern Analysis and Machine Intelligence, PP(99):11, 2017, pp. 1--1.

[3]

M. D. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q. V. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean et al., "On rectified linear units for speech processing,", 2013, pp. 3517--3521.

[4]

M. W. B. N. R. H. T. Li, H. Chang and S. Yan, "Crowded scene analysis: A survey," in IEEE transactions on circuits and systems for video technology, 2015, p. 25(3):367386.

[5]

D. Onoro-Rubio and R. J. Lopez-Sastre, "Towards perspective-free object counting with deep learning," in European Conference on Computer Vision, 2016, p. 615629.

[6]

J. P. C. S. Zhang, G. Wu and J. M. Moura, "Understanding traffic density from large-scale web camera data," in arXiv preprint arXiv:1703.05868, 2017.

[7]

A. A. J. Johnson and L. Fei-Fei, "Perceptual losses for real-time style transfer and super-resolution," in European Conference on Computer Vision, 2016, p. 694711.

[8]

H. Idrees, I. Saleemi, C. Seibert, and M. Shah. Multisource multi-scale counting in extremely dense crowd images. In CVPR, 2013.

Digital Library

[9]

S. S. K. L. Boominathan and R. V. Babu, "Crowdnet: A deep convolutional network for dense crowd counting," in Proceedings of the ACM on Multimedia Conference, 2016, p. 640644.

Digital Library

[10]

X. W. X. Y. C. Zhang, H. Li, "Cross-scene crowd counting via deep convolutional neural networks." IEEE, 2015, pp. 833--841.

[11]

Y. J. P. S. S. R. D. A.-D. E. V. V. A. R. C. Szegedy, W. Liu, "Going deeper with convolutions," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1--9.

[12]

A. Z. K. Simonyan, "Very deep convolutional networks for largescale image recognition."

[13]

S. Y. M. Lin, Q. Chen, "Network in network," in arXiv preprint arXiv:1312.4400.

[14]

B. Wu and R. Nevatia, "Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors," in IEEE International Conference on Computer Vision. IEEE, 2005, p. 9097.

Digital Library

[15]

V. A. Sindagi and V. M. Patel, "Cnn-based cascaded multi-task learning of high-level prior and density estimation for crowd counting," in Advanced Video and Signal Based Surveillance (AVSS), 2017 14th IEEE International Conference on. IEEE, 2017, pp. 1--6.

[16]

S. S. Deepak Babu Sam and R. V. Babu, "Switching convolutional neural network for crowd counting," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1.IEEE, 2017, p. 6.

[17]

R. Stewart and M. Andriluka, "End-to-end people detection in crowded scenes," in arXiv preprint arXiv:1506.04878, 2015.

[18]

G. J. Brostow and R. Cipolla, "Unsupervised bayesian detection of independent motion in crowds," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, 2006, p. 594601.

Digital Library

[19]

V. Rabaud and S. Belongie, "Counting crowded moving objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2006, vol. 11, p. 705711.

Digital Library

[20]

C. S. H. Idrees, I. Saleemi and M. Shah, "Multi-source multi-scale counting in extremely dense crowd images," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2013, p. 25472554.

Digital Library

[21]

O. Y. V.-Q. Pham, T. Kozakaya and R. Okada, "Count forest: Covoting uncertain number of targets using random forest for crowd density estimation," in ICCV, 2015.

Digital Library

[22]

S. L. Mark Marsden, Kevin McGuiness and N. E. OConnor, "Fully convolutional crowd counting on highly congested scenes," in arXiv preprint arXiv: 1612.00220, 2016.

[23]

L. Y. S. L. C. Wang, H. Zhang and X. Cao, "Deep people counting in extremely dense crowds," in Proceedings of the ACM on Multimedia Conference, 2015, p. 12991302.

Digital Library

[24]

D. Onoro-Rubio and R. J. Lopez-Sastre, "Towards perspective-free object counting with deep learning," in European Conference on Computer Vision, 2016, p. 615629.

[25]

S. G. K. Chen, C. C. Loy and T. Xiang, "Feature mining for localised crowd counting," in BMVC, 2012.

[26]

R. G. S. Ren, K. He and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," in NIPS, 2015.

Digital Library

Cited By

IMAI RYAMAMOTO YJIANG WNAKAHARA MKAMIYA DNOMURA K(2024)ESTIMATING CROWD SIZE USING MULTIPLE HEADCOUNTING METHODS AND REGRESSION ANALYSIS複数の人数計数手法と回帰分析を用いた群衆人数の推定Japanese Journal of JSCE10.2208/jscejj.23-2201080:22(n/a)Online publication date: 2024
https://doi.org/10.2208/jscejj.23-22010
IMAI RYAMAMOTO YJIANG WNAKAHARA MKAMIYA DNOMURA K(2023)CONSIDERATION ON THE BEST METHOD TO COUNT THE NUMBER OF PEOPLE DEPENDING ON THE STATUS OF CROWDS群衆の状態に応じた最適な人数計数手法に関する一考察Japanese Journal of JSCE10.2208/jscejj.22-2202579:22(n/a)Online publication date: 2023
https://doi.org/10.2208/jscejj.22-22025
Tripathy SKaushik NSrivastava SSrivastava R(2023)Crowd Counting via De-background Multicolumn Dynamic Convolutional Neural NetworkComputational Intelligence for Modern Business Systems10.1007/978-981-99-5354-7_23(435-453)Online publication date: 4-Nov-2023
https://doi.org/10.1007/978-981-99-5354-7_23
Show More Cited By

Index Terms

Crowd Counting using DMCNN
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems

Recommendations

Arbitrary perspective crowd counting via local to global algorithm
Abstract
Crowd counting is getting more and more attention. More and more collective activities, such as the Olympics Games and the World Expo, are also important to control the crowd number. In this paper, we address the problem of crowd counting in the ...
DCGSA: A global self-attention network with dilated convolution for crowd density map generating
Abstract
Due to non-uniform density and variations in scale and perspective, estimating crowd count in crowded scenes in different degree is an extremely challenging task. The deep learning models mostly use pooling operation so that the ...
An efficient multi-scale contextual feature fusion network for counting crowds with varying densities and scales
Abstract
The crowd counting problem aims to predict the number of pedestrians in a surveillance video or an image and produce a crowd density map. Achieving accurate crowd counting in different crowded scenes is still challenging due to drastic scale ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICIAI '19: Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence

March 2019

279 pages

ISBN:9781450361286

DOI:10.1145/3319921

Copyright © 2019 ACM.

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]

In-Cooperation

Xi'an Jiaotong-Liverpool University: Xi'an Jiaotong-Liverpool University
University of Texas-Dallas: University of Texas-Dallas

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 March 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICIAI 2019

ICIAI 2019: 2019 The 3rd International Conference on Innovation in Artificial Intelligence

March 15 - 18, 2019

Suzhou, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
146
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)3

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

IMAI RYAMAMOTO YJIANG WNAKAHARA MKAMIYA DNOMURA K(2024)ESTIMATING CROWD SIZE USING MULTIPLE HEADCOUNTING METHODS AND REGRESSION ANALYSIS複数の人数計数手法と回帰分析を用いた群衆人数の推定Japanese Journal of JSCE10.2208/jscejj.23-2201080:22(n/a)Online publication date: 2024
https://doi.org/10.2208/jscejj.23-22010
IMAI RYAMAMOTO YJIANG WNAKAHARA MKAMIYA DNOMURA K(2023)CONSIDERATION ON THE BEST METHOD TO COUNT THE NUMBER OF PEOPLE DEPENDING ON THE STATUS OF CROWDS群衆の状態に応じた最適な人数計数手法に関する一考察Japanese Journal of JSCE10.2208/jscejj.22-2202579:22(n/a)Online publication date: 2023
https://doi.org/10.2208/jscejj.22-22025
Tripathy SKaushik NSrivastava SSrivastava R(2023)Crowd Counting via De-background Multicolumn Dynamic Convolutional Neural NetworkComputational Intelligence for Modern Business Systems10.1007/978-981-99-5354-7_23(435-453)Online publication date: 4-Nov-2023
https://doi.org/10.1007/978-981-99-5354-7_23
Thai TLy N(2020)Lightweight solution to background noise in crowd counting2020 7th NAFOSTED Conference on Information and Computer Science (NICS)10.1109/NICS51282.2020.9335834(185-190)Online publication date: 26-Nov-2020
https://doi.org/10.1109/NICS51282.2020.9335834
Deng LWang SZhang Y(2020)Fully Optimized Convolutional Neural Network Based on Small-Scale Crowd2020 IEEE International Symposium on Circuits and Systems (ISCAS)10.1109/ISCAS45731.2020.9180823(1-5)Online publication date: Oct-2020
https://doi.org/10.1109/ISCAS45731.2020.9180823
Zhao PAdnan KLyu XWei SSinnott R(2020)Estimating the Size of Crowds through Deep Learning2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)10.1109/CSDE50874.2020.9411377(1-8)Online publication date: 16-Dec-2020
https://doi.org/10.1109/CSDE50874.2020.9411377

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten