Skip to main content
SpringerLink
Log in

Survey on algorithms of people counting in dense crowd and crowd density estimation

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The number of people and the estimation of the population density are one of the important information concerned by intelligent monitoring. This article reviews, summarizes, and classifies the research methods and status of population statistics and population density estimation. According to the different methods of obtaining crowd information, the research methods of population density statistics and population density estimation are divided into detection-based methods, regression-based methods, and density-based methods. The methods based on density estimation are studied in detail. The network structures based on density estimation are divided into a single-column deep convolutional neural network and a multi-column convolutional neural network. Summarized the basic ideas, advantages and disadvantages of each method, analyzed and introduced the representative algorithms of each method, analyzed and compared related experiments, and introduced common mainstream data sets and performance evaluations for population statistics and population density estimation. Indicators and evaluation methods, and prospects for future possible research directions and corresponding development trend in this field.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Data availability

Not applicable.

Abbreviations

SVM:

Support vector machine

HOG:

Histograms of oriented gradients

MID:

Mosaic image difference

DNN:

Deep convolutional neural networks

GPU:

Graphics processing unit

FPGA:

Field programmable gate array

ASIC:

Application specific integrated circuit

VGG:

Visual geometry group

ResNet:

Recurrent neural network structure

CCNN:

Counting convolutional neural networks

MAE:

Mean absolute error

MSE:

Mean squared error

References

  1. Albiol A, Silla MJ, Mossi JM (2009) Video analysis using corner motion statistics[C]. Proc of IEEE international workshop on performance evaluation of tracking and surveillance, pp 31–38

  2. Bai C, Chen JN, Huang L et al (2018) Saliency-based multi-feature modeling for semantic image retrieval[J]. J Vis Commun Image Represent 15(3):199–204

  3. Bansal M, Kumar M, Kumar M (2021) 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors[J]. Multimed Tools Appl 80(12):18839–18857

    Article  Google Scholar 

  4. Bansal M, Kumar M et al (2021) An efficient technique for object recognition using shi-tomasi corner detection algorithm[J]. Soft Comput 25(6):4423–4432

  5. Biswas S, Hazra R (2018) Robust edge detection based on modified moore-neighbor[J]. Optik 10(1):11–21

  6. Boominathan L, Kruthiventi SS, Babu VR (2016) CrowdNet: a deep convolutional network for dense crowd counting[C]. ACM on multimedia conference, pp 75–83

  7. Carmona JM, Climent J (2018) Human action recognition by means of subtensor projections and dense trajectories[J]. Pattern Recogn 14(2):11–19

  8. Chen LC, Papandreou G, Kokkinos I et al (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Trans Pattern Anal Mach Intell 40(4):834

  9. Dargan S, Kumar M, Kumar GA (2020) Survey of deep learning and its applications: a new paradigm to machine learning. Archives of computational methods in engineering[J]. Arch Comput Methods Eng 27(4):1071–1092

  10. Dharanipragada NVRA, Galvita VV, Poelman H et al (2018) Insight in kinetics from pre-edge features using time resolved in situ XAS[J]. AIChE J 64(2):64–72

    Google Scholar 

  11. Dng X, Lin Z, He F et al (2018) A deeply-recursive convolutional network for crowd counting[J]. IEEE Trans Neural Networks Learn Syst 34(8):11–23

  12. Dolz J, Ayed IB, Yuan J et al (2018) HyperDense-Net: a hyper-densely connected CNN for multi-modal image semantic segmentation[J]. IEEE Trans Med Imaging 16(3):34–41

  13. Fiaschi L, Nair R, Koethe U et al (2012) Learning to count with regression forest and structured labels[C]. International Conference on Pattern Recognition (ICPR), pp 539–545

  14. Gao F, Song X, Jian L et al (2019) Toward budgeted online Kernel ridge regression on streaming data[J]. IEEE Access 17(3):11–19

  15. Gong L, Zhang C, Duan L, Du X, Liu H, Chen X, Zheng J (2019) Nonrigid image registration using spatially region-weighted correlation ratio and GPU-acceleration[J]. IEEE J Biomedical Health Inf 17(5):66–78

  16. Gupta S, Thakur K, Kumar M (2021) 2D-human face recognition using SIFT And SURF descriptors of face’s feature regions[J]. Visual Comput 37(3):447–456

  17. Hao Xue DuQ, Huynh, Mark Reynolds (2021) PoPPL: pedestrian trajectory prediction by LSTM with automatic route class clustering[J]. IEEE Trans Neural Networks Learn Syst 32(1):77–90

  18. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition[C]. IEEE conference on computer vision & pattern recognition. IEEE Computer Society, pp 47–54

  19. He Y, Yang T, Lu Y et al (2018) Specific shape feature for fast pedestrian detection in cascade way[C]. IEEE advanced information management, communicates, electronic & automation control conference, pp 57–64

  20. Hu H, Lu YM (2019) Asymptotics and optimal designs of SLOPE for sparse linear regression[C]. IEEE international symposium on information theory. IEEE, pp 324–331

  21. Huang Y, Jia P, Cai D et al (2019) Perception evaluation: a new solar image quality metric based on the multi-fractal property of texture features[J]. Sol Phys 29(9):294–303

  22. Huang L, Zhu L, Shen S (2021) SRNet: scale-aware representation learning network for dense crowd counting[J]. IEEE Access 9:136032–136044

  23. Kumar A, Kumar M, Kaur A (2021) Face detection in still images under occlusion and non-uniform illumination[J]. Multimed Tools Appl 80(10):14565–14590

  24. Li T, Chang H, Wang M et al (2015) Crowded scene analysis: a survey[J]. IEEE Trans Circuits Syst Video Technol 12(7):67–86

    Google Scholar 

  25. Li Y, Claesen L, Huang K et al (2018) A real-time high-quality complete system for depth image-based rendering on FPGA[J]. IEEE Trans Circuits Syst Video Technol 29(7):12–17

  26. Li Y, Zhang X, Chen D (2018) CSRNet: dilated convolutional neural networks for understanding the highly congested scenes[J]. IEEE Trans Affect Comput 33(2):1–16

  27. Liang X, Zhang J, Tian Q et al (2018) A saliency guided shallow convolutional neural network for traffic signs retrieval[C]. 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp 124–133

  28. Lu R, Ma (2019) Huimin. semantic head enhanced pedestrian detection in a crowd[C]. IEEE computer society conference on computer vision & pattern recognition, pp 11–19

  29. Lu R, Ma H (2019) Occluded pedestrian detection with visible iou and box sign predictor[C]. 2019 IEEE International Conference on Image Processing (ICIP). IEEE, pp 27–35

  30. Marsden M, Mcguinness K, Little S et al (2016) Fully convolutional crowd counting on highly congested scenes[J]. IEEE Trans Pattern Anal Mach Intell 35(9):11–19

  31. Martinho-Corbishley D, Nixon M, Carter JN (2018) Super-fine attributes with crowd prototyping[J]. IEEE Trans Pattern Anal Mach Intell 17(5):24–31

  32. Ooro-Rubio D, Roberto J, López-Sastre (2016) Towards perspective-free object counting with deep learning[C]. European Conference on Computer Vision (ECCV). Springer, Cham, pp 137–143

  33. Pham VQ, Kozakaya T, Yamaguchi O et al (2015) COUNT Forest: co-voting uncertain number of targets using random forest for crowd density estimation[C]. International conference on computer vision, pp 54–61

  34. Rodriguez M, Laptev I, Sivic J et al (2011) Density-aware person detection and tracking in crowds[C]. IEEE international conference on computer vision, pp 77–84

  35. Rota L, Michele C, Balzer MN et al (2018) Development of a front-end ASIC for 1D detectors with 12 MHz frame-rate[C]. Topical workshop on electronics for particle physics, pp 521–528

  36. Sabzmeydani P, Mori G (2013) Detecting pedestrians by learning shaplet features[C]. IEEE computer society conference on computer vision and pattern recognition, pp 1–8

  37. Sam DB, Surya S, Babu RV (2017) Switching convolutionalneural network for crowd counting[C]. 2017 IEEE Conference on Computer Visionand Pattern Recognition (CVPR), pp 241–247

  38. Schulz E, Speekenbrink M, Krause A (2018) A tutorial on gaussian process regression: modelling, exploring, and exploiting functions[J]. J Math Psychol 13(6):1–16

  39. Shi C, Luo G (2018) A compact VLSI system for bio-inspired visual motion estimation[J]. IEEE Trans Circuits Syst Video Technol Publication Circuits Syst Soc 28(4):10–17

  40. Shirvaikar MV, Grecos C, Maheshwary P (2018) Blind image sharpness metric based on edge and texture features[C]. Real-time image &video processing, pp 481–489

  41. Sindagi VA, Patel VM (2017) CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting[J]. IEEE Trans Neural Networks Learn Syst 52(8):45–58

  42. Song T-A, Chowdhury SR, Yang F, Dutta J (2020) Super-resolution PET imaging using convolutional neural networks[J]. IEEE Trans Comput Imaging 6:518–528

  43. Tahboub K, Reibman AR, Delp EJ (2018) Accuracy prediction for pedestrian detection[C]. IEEE international conference on image processing. IEEE, pp 37–46

  44. Tsalapati E, Stoilos G, Stamou G et al (2018) Efficient query answering over expressive inconsistent description logics[C]. International joint conference of artificial intelligence, pp 94–102

  45. Wang Y, Zou Y (2016) Fast visual object counting via example-based density estimation[C]. IEEE International Conference on Image Processing (ICIP), pp 223–231

  46. Xu B, Qiu G (2016) Crowd density estimation based on rich features and random projection forest[C]. 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 432–439

  47. Xu M, Ge Z, Jiang X et al (2019) Depth information guided crowd counting for complex crowd scenes[J]. Pattern Recognit Lett 22(7):563–569

  48. Yousaf RM, Habib HA, Dawood H et al (2018) A comparative study of various edge detection methods[C]. 14th International Conference on Computational Intelligence and Security (CIS), pp 768–773

  49. Yukun Tian Y, Lei J, Zhang JZ, Wang (2020) PaDNet: pan-density crowd counting[J]. IEEE Trans Image Process 29:2714–2727

  50. Zeng L, Xu X, Cai B et al (2017) Multi-scale convolutional neural networks for crowd counting[J]. IEEE Trans Pattern Anal Mach Intell 35(9):14–20

  51. Zhang C, Li H, Wang X et al (2015) Cross-scene crowd counting via deep convolutional neural networks[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 329–337

  52. Zhang C, Li H, Wang X et al (2015) Cross-scene crowd counting via deep convolutional neural networks[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 251–259

  53. Zhang Y, Zhou D, Chen S et al (2016) Single-image crowd counting via multi-column convolutional neural network[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 83–89

  54. Zhang X, Sun H, Chen S et al (2019) NIPM-sWMF: toward efficient FPGA design for high-definition large-disparity stereo matching[J]. IEEE Trans Circuits Syst Video Technol 32(7):30–43

  55. Zhao S, Yang W, Wang Y (2018) A new hand segmentation method based on fully convolutional network[C]. Chinese control & decision conference. IEEE, pp 632–639

  56. Zhou Z, Zhao G, Kijowski R et al (2018) Deep convolutional neural network for segmentation of knee joint anatomy[J]. Magn Reson Med 33(2):19–27

  57. Zhou RG, Yu H, Cheng Y et al (2019) Quantum image edge extraction based on improved prewitt operator[J]. Quantum Inf Process 13(2):18–27

Download references

Acknowledgements

Thanks to the anonymous reviewers for their constructive suggestions to help improve this article.

Funding

This research was financially supported by Major Scientific Research Project for Universities of Guangdong Province (2019KZDXM015, 2020ZDZX3058); Guangdong Provincial special funds Project for Discipline Construction (No.2013WYXM0122); Science and technology projects of Zhuhai in the field of social development (2220004000066); Key Laboratory of Intelligent Multimedia Technology(201762005).

Author information

Authors and Affiliations

  1. Research Center for Intelligent Engineering and Educational Application, Beijing Normal University, Zhuhai, 519087, China

    Ge Yang & Dian Zhu

  2. Key Laboratory of Intelligent Multimedia Technology, Beijing Normal University, Zhuhai, 519087, China

    Ge Yang & Dian Zhu

  3. Engineering Lab on Intelligent Perception for Internet of Things (ELIP), Shenzhen Graduate School, Peking University, Shenzhen, 518055, China

    Ge Yang

Authors
  1. Ge Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dian Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The first author (YG) participated in the designing of the article, and composed the manuscript. The second author (ZD) conceived of the study, participated in the design, and helped to draft the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Ge Yang.

Ethics declarations

Competing interests

None.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, G., Zhu, D. Survey on algorithms of people counting in dense crowd and crowd density estimation. Multimed Tools Appl 82, 13637–13648 (2023). https://doi.org/10.1007/s11042-022-13957-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-13957-y

Keywords

Search

Navigation