Skip to main content
SpringerLink
Log in

Traffic density estimation via a multi-level feature fusion network

  • Published:
Applied Intelligence Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Traffic density estimation plays a positive role in improving the traffic efficiency of contemporary cities. Accurate estimation of traffic flow density can provide effective information for traffic dispatching command and effectively alleviate road traffic congestion. However, due to the problems of perspective distortion, scale change, serious occlusion and background interference in traffic video images, it brings great challenges to traffic density estimation. To solve the above problems, this paper constructs a traffic density estimation network based on multi-level fusion network (MFNet). Firstly, the low-level feature map and high-level feature map after Depthwide convolution Block (DCB) are combined to fuse features of different scales, which solves the problems of perspective distortion and scale change in the image; Then, the fused feature map is sent to the channel attention mechanism module to realize the smooth transition between pixels; Finally, by restoring the location information of the vehicle space on the density map and combining with the estimated number of vehicles, the traffic density is calculated quantitatively. In addition, our network also uses multiple superimposed dilated convolutions to obtain high-quality density map. Experimental results show that the Gride Average Mean absolute Error (GAME) metric of the proposed method is reduced to 14.32 on the TRANCOS dataset. Compared with the existing traffic density estimation methods, the estimation accuracy is significantly improved, especially in the case of serious perspective distortion and vehicle height overlap.

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
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Zheng Y, Peng S (2012) Model based vehicle localization for urban traffic surveillance using image gradient based matching, Presented at International IEEE Conference on Intelligent Transportation Systems. https://ieeexplore.ieee.org/document/6338660

  2. Toropov E, Gui L, Zhang S, et al (2015) Traffic flow from a low frame rate city camera, Presented at IEEE International Conference on Image Processing (ICIP). IEEE 2015: 3802–3806

  3. Zhang T, Automation SO (2014) Modeling and Analysis of Vehicle Flow Detection Based on Video. Computer and Digital Engineering

  4. Abdelwahab MA (2018) Fast approach for efficient vehicle counting. Electronics Letters. 20–22

  5. Liu Y, Tian B, Chen S, Zhu F, Wang K (2013) A survey of vision-based vehicle detection and tracking techniques in ITS. IEEE International Conference on Vehicular Electronics and Safety. https://doi.org/10.1109/ICVES.2013.6619606

    Article  Google Scholar 

  6. Zhang Z, Liu K, Gao F, Li X, Wang G (2016) Vision-based vehicle detecting and counting for traffic flow analysis. International Joint Conference on Neural Networks. http://ieeexplore.ieee.org/document/7727480/

  7. Maitra M, Gupta RK, Mukherjee M (2012) Detection and counting of red blood cells in blood cell images using Hough transform, International journal of computer applications

  8. Rabaud V, Belongie S (2006). Counting crowded moving objects. Presented at Conference on Computer Vision and Pattern Recognition [CVPR'06]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=1640823

  9. Tu P, Sebastian T, Doretto T et al, (2008) Unified crowd segmentation. European Conference on Computer Vision. https://link.springer.com/chapter/10.1007%2F978-3-540–88693–8_51

  10. Kothari S, Chaudry Q, Wang MD (2009) Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques. IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2009:795–798

    Google Scholar 

  11. Shang C, Ai H, Bai B (2016) End-to-end crowd counting via joint learning local and global count. 2016 IEEE International Conference on Image Processing. https://ieeexplore.ieee.org/document/7532551

  12. Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions, Proceedings of the IEEE conference on computer vision and pattern recognition, 1–9.

  13. Walach E, Wolf L (2016) Learning to Count with CNN Boosting, European conference on computer vision. https://link.springer.com/chapter/10.1007%2F978-3-319-46475-6_41

  14. Marsden M, McGuinness K, Little S et al (2018) People, penguins and petri dishes: Adapting object counting models to new visual domains and object types without forgetting, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 8070–8079

  15. Zhang S, Wu G, Costeira JP et al (2017) Fcn-rlstm: Deep spatio-temporal neural networks for vehicle counting in city cameras, Proceedings of the IEEE international conference on computer vision, 3667–3676

  16. Fiaschi L, Köthe U, Nair R, et al (2012) Learning to count with regression forest and structured labels, 21st International Conference on Pattern Recognition. http://ieeexplore.ieee.org/document/6460719

  17. Zhang S, Wu G, Costeira JP et al (2017) Understanding traffic density from large-scale web camera data, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

  18. Zhang C, Li H, Wang X et al Cross-scene crowd counting via deep convolutional neural networks, IEEE conference on computer vision and pattern recognition. https://ieeexplore.ieee.org/document/7298684

  19. Xie W, Noble JA, Zisserman A (2018) Microscopy cell counting and detection with fully convolutional regression networks, Computer methods in biomechanics and biomedical engineering: Imaging & Visualization 283–292

  20. Zhang Y, Zhou D, Chen S et al (2016) Single-image crowd counting via multi-column convolutional neural network. IEEE conference on computer vision and pattern recognition. https://ieeexplore.ieee.org/document/7780439

  21. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks, IEEE conference on computer vision and pattern recognition. https://ieeexplore.ieee.org/document/8578843

  22. Von Borstel M, Kandemir M, Schmidt P et al (2016) Gaussian process density counting from weak supervision, European Conference on Computer Vision. https://link.springer.com/chapter/10.1007/978-3-319-46448-0_22

  23. Onoro-Rubio D, López-Sastre RJ (2016) Towards perspective-free object counting with deep learning, European Conference on Computer Vision. https://link.springer.com/chapter/10.1007/978-3-319-46478-7_38

  24. Wang Y, Hu S, Wang G et al (2020) Multi-scale dilated convolution of convolutional neural network for crowd counting. Multimedia Tools and Applications 1057–1073

  25. Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions, arXiv preprint arXiv

  26. Lempitsky V, Zisserman A (2010) Learning to count objects in images, Advances in neural information processing systems. https://www.researchgate.net/publication/311396316_ Learning_to_count_objects_in_images

  27. Wang C, Zhang H, Yang L, et al (2015) Deep people counting in extremely dense crowds, Proceedings of the 23rd ACM international conference on Multimedia, 1299–1302

  28. Li Y, Zhang X, Chen D (2018) CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes, Proceedings of the IEEE conference on computer vision and pattern recognition, 1901–1100

  29. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv

  30. Guerrero-Gómez-Olmedo, Torre-Jiménez RB, López-Sastre R et al (2015) Extremely overlapping vehicle counting, Iberian Conference on Pattern Recognition and Image Analysis., https://link.springer.com/chapter/10.1007%2F978-3-319–19390–8_48

  31. Zhang A, Shen J, Xiao Z et al (2019) Relational attention network for crowd counting, IEEE International Conference on Computer Vision. https://ieeexplore.ieee.org/document/9010829/citations

  32. Zhang Y, Zhou C, Chang F et al (2018) Multi-resolution attention convolutional neural network for crowd counting. 144–152

  33. Yu S, Pu J (2020) Aggregated context network for crowd counting. Frontiers of Information Technology & Electronic Engineering 1–13

Download references

Acknowledgements

The authors are grateful for collaborative funding support from the Humanity and Social Science Foundation of Ministry of Education, China (21YJAZH077).

Author information

Authors and Affiliations

  1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266590, China

    Rui-Sheng Jia, Yong-Chao Li, Qi Zhang & Hong-Mei Sun

  2. Shandong Province Key Laboratory of Wisdom Mine Information Technology, Shandong University of Science and Technology, Qingdao, 266590, China

    Hong-Mei Sun

Authors
  1. Ying-Xiang Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rui-Sheng Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yong-Chao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hong-Mei Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Rui-Sheng Jia or Hong-Mei Sun.

Additional information

Publisher's note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, YX., Jia, RS., Li, YC. et al. Traffic density estimation via a multi-level feature fusion network. Appl Intell 52, 10417–10429 (2022). https://doi.org/10.1007/s10489-022-03188-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03188-x

Keywords

Search

Navigation