International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Density Change Adaptive Congestive Scene Recognition Network

  • Jun-Hee Kim (Dept. of Electronic Engineering, Dongseo University) ;
  • Dae-Seok Lee (Buil Planning Co.) ;
  • Suk-Ho Lee (Dept. Artificial Intelligence Appliance, Dongseo University)
  • Received : 2023.10.14
  • Accepted : 2023.10.25
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In recent times, an absence of effective crowd management has led to numerous stampede incidents in crowded places. A crucial component for enhancing on-site crowd management effectiveness is the utilization of crowd counting technology. Current approaches to analyzing congested scenes have evolved beyond simple crowd counting, which outputs the number of people in the targeted image to a density map. This development aligns with the demands of real-life applications, as the same number of people can exhibit vastly different crowd distributions. Therefore, solely counting the number of crowds is no longer sufficient. CSRNet stands out as one representative method within this advanced category of approaches. In this paper, we propose a crowd counting network which is adaptive to the change in the density of people in the scene, addressing the performance degradation issue observed in the existing CSRNet(Congested Scene Recognition Network) when there are changes in density. To overcome the weakness of the CSRNet, we introduce a system that takes input from the image's information and adjusts the output of CSRNet based on the features extracted from the image. This aims to improve the algorithm's adaptability to changes in density, supplementing the shortcomings identified in the original CSRNet.

Keywords

Acknowledgement

This research was supported by 「Fostering Project of R&D promotion complex in Busan」 funded by the Korea government(MSIT) and a local government(Busan)(2023-Development of R&D promotion complex-BUSAN-Segment1-Scaleup1)

References

  1. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, D. Ramanan, "Object detection with discriminatively trained part-based models," IEEE transactions on pattern analysis and machine intelligence, Vol. 32, No. 9, pp.1627-1645, DOI:https://doi.org/2010.10.1109/TPAMI.2009.167
  2. H. Idrees, I. Saleemi, C. Seibert, M. Shah, "Multi-source multi-scale counting in extremely dense crowd images," In Proc. of International Conference on Computer Vision and Pattern Recognition, pp. 2547-2554, June 25-26, 2013. DOI:https://doi.org/10.1109/CVPR.2013.329
  3. A. B. Chan, N. Vasconcelos, "Bayesian poisson regression for crowd counting," In Proc. of International Conference on Computer Vision, pp. 545-551, Sep. 29-Oct. 2, 2009. DOI:https://doi.org/10.1109/ICCV.2009.5459191
  4. V. Lempitsky, A. Zisserman, "Learning to count objects in images," In Advances in Neural Information Processing Systems, pp. 1324-1332, Dec. 6-11, 2010.
  5. V.Q. Pham, T. Kozakaya, O. Yamaguchi, R. Okada, "Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation," In Proc. International Conference on Computer Vision, pp. 3253-3261, Dec. 11-18, 2015. DOI:https://doi.org/10.1109/ICCV.2015.372
  6. Y. Zhang, D. Zhou, S. Chen, S. Gao, Y. Ma, "Single-image crowd counting via multi-column convolutional neural network," in Proc. of the IEEE conference on computer vision and pattern recognition, pp. 589-597, June 27-30, 2016. DOI:https://doi.org/10.1109/CVPR.2016.70
  7. V. A. Sindagi, V. M. Patel, "Generating high quality crowd density maps using contextual pyramid CNNs," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1861-1870, Oct. 22-29, 2017. DOI:https://doi.org/10.1109/ICCV.2017.206
  8. D. B. Sam, S. Surya, R. V. Babu, "Switching convolutional neural network for crowd counting," in Proc. of Conference on Computer Vision and Pattern Recognition, pp. 5744-5752, July 21-26, 2017. DOI:https://doi.org/10.1109/CVPR.2017.429
  9. Y. Zhang, D. Zhou, S. Chen, S. Gao, and Y. Ma, "Single-image crowd counting via multi-column convolutional neural network," in Proc. of Conference on Computer Vision and Pattern Recognition,, pp. 589-597, June 27-30, 2016. DOI:https://doi.org/10.1109/CVPR.2016.70
  10. L. Yuhong, X. Zhang, and D. Chen, "Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes," in Proc. of the IEEE conference on computer vision and pattern recognition, pp. 1091-1100, June 18-23, 2018. DOI:https://doi.org/10.1109/CVPR.2018.00120
  11. V. Ashish, et al. "Attention is all you need," in Advances in neural information processing systems, pp. 5998-6008, Dec. 4-7, 2017.