Skip to main content

Advertisement

SpringerLink
Log in

Detection of crowdedness in bus compartments based on ResNet algorithm and video images

  • 1193: Intelligent Processing of Multimedia Signals
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The crowding in bus is an important factor affecting passenger satisfaction and bus dispatching level. However, how to use video images to detect crowding accurately is a difficult problem. In this paper, firstly, an image sample library is established based on the evaluation standard of crowding in bus, which contains 16346 sample images. Then, Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) are used to extract the texture features of the image in bus. Then, a rough classification method of crowding based on Support Vector Machine (SVM) is proposed. At the same time, in order to improve the accuracy of rough classification of crowding, the optimization effects of grid search algorithm, particle swarm optimization algorithm and genetic algorithm on SVM parameters are compared. The results show that the optimization effect of genetic algorithm is the best, and the accuracy rate is 93.20%. Finally, for the problem that the SVM method is not ideal in the fine classification of crowding, this paper proposes a new method based on ResNet. SGD, Adadelta and Adam are selected to optimize the parameters of ResNet model. The accuracy of the optimal Adam algorithm reaches 96.22%, which effectively solves the problem of the fine classification of crowding in bus.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Azencott R, Wang JP, Younes L (1997) Texture classification using windowed Fourier filters[J]. IEEE Trans Pattern Anal Mach Intell 19(2):148–153

    Article  Google Scholar 

  2. Bai H, Liu H, Ni H et al (2012) Bus fare classification with genetic algorithm[J]. Transp Syst Eng Inform 12(1):180–184

    Google Scholar 

  3. Kittelson & Assoc, Inc., Parsons Brinckerhoff, Inc., KFH Group, Inc., Texam A&M Transportation Institute, & Arup (2013) Transit capacity and quality of service manual. Third Edition [M]. Transportation Research Board

  4. Chow TWS, Cho SY (2002) Industrial neural vision system for underground railway station platform surveillance[C]. Adv Eng Inform 16(1):73–83

    Article  Google Scholar 

  5. Chow TWS, Yam JYF, Cho SY (1999) Fast training algorithm for feedforward neural networks: Application to crowd estimation at underground stations[J]. Artif Intell Eng 13(3):301–307

    Article  Google Scholar 

  6. Comer ML, Delp EJ (1999) Segmentation of textured images using a multiresolution Gaussian autoregressive model[J]. IEEE Trans Image Process 8(3):408–420

    Article  Google Scholar 

  7. Cortes C, Vapnik V (1995) Support-vector networks[J]. Mach Learn 20(3):273–297

    MATH  Google Scholar 

  8. Cover TM, Hart PE (1967) Nearest neighbor pattern classification[J]. IEEE Trans Inf Theory 13(1):21–27

    Article  Google Scholar 

  9. Davies AC, Yin JH, Velastin SA (1995) Crowd monitoring using image processing[J]. Electron Commun Eng J 7(1):37–47

    Article  Google Scholar 

  10. Haralick RM, Shanmugam K (1973) Texture features for image classification[J]. IEEE Trans Syst Man Cybern 3(6):610–621

    Article  Google Scholar 

  11. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition[C]. Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, pp 770-778

  12. Huang L, Wu N, Wang X et al (2019) Research on classroom face recognition based on feature vector extraction and SVM classifier[J]. Instrum Cust 26(2):15–17

    Google Scholar 

  13. Lameski P, Zdravevski E, Mingov R et al (2015) SVM Parameter Tuning with Grid Search and Its Impact on Reduction of Model Over-fitting[M]. Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing. Springer International Publishing

  14. Li Z (2020) Research on bus congestion detection based on video image [D]. Beijing Jiaotong University, Beijing

    Google Scholar 

  15. Li Z, Han J, Zhao X et al (2015) Comparison of drunk driving recognizing methods based on KNN and SVM [J]. J Transp Syst Eng Inf Technol 15(5):246–251

    Google Scholar 

  16. Li B, Han X, Dongmei W (2018) Real-time crowd density estimation based on convolutional neural networks [J]. J Graph 39(4):728–734

    Google Scholar 

  17. Marana AN, Velastin SA, Costa LF et al (1997) Estimation of crowd density using image processing[C]. IEE Colloquium on Image Processing for Security Applications (Digest No: 1997/074), London, pp 11/1-11/8

  18. Marana AN, Costa LF, Lotufo RA et al (1998) On the efficacy of texture analysis for crowd monitoring[C]. International Symposium on Computer Graphics. IEEE Computer Society, pp 354-361.

  19. Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Trans Pattern Anal Mach Intell 24(7):971–987

    Article  Google Scholar 

  20. Sam DB, Surya S, Babu R V (2017) Switching Convolutional Neural Network for Crowd Counting[C]. Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, pp 4031-4039

  21. Shi X, Huang Q, Chang J et al (2015) Optimal parameters of the SVM for temperature prediction[J]. Proc Int Assoc Hydrol Sci 368:162–167

    Google Scholar 

  22. Simard M, Saatchi SS, De Grandi G (2000) The use of decision tree and multiscale texture for classification of JERS-1 SAR data over tropical forest[J]. IEEE Trans Geosci Remote Sens 38(5):2310–2321

    Article  Google Scholar 

  23. Sindagi V A, Patel V M (2017) Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs[C]. International Conference on Computer Vision (ICCV), Venice, pp 1879-1888

  24. Tang Y, Lu W, Cheng C et al (2019) Illumination Calculation Method Based on Adam Algorithm and Neural Network[J]. China Illum Eng J 30(2):50–54

    Google Scholar 

  25. Wang Y (2013) Research on population density estimation algorithm based on gray symbiosis matrix [D]. Xi’an University of Science and Technology, Shaanxi

    Google Scholar 

  26. Wu M, Huang H, Wang X (2018) Robot welding path planning based on improved ant colony algorithm[J]. Trans J China Weld Inst 39(10):113–118

    Google Scholar 

  27. Zhang X, Guo Y (2009) Optimization of SVM Parameters Based on PSO Algorithm[C]. International Conference on Natural Computation. IEEE Press, pp 536-539

  28. Zhang C, Li H, Wang X, et al (2015) Cross-scene crowd counting via deep convolutional neural networks[C]. Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp 833-841

  29. Zhang Y, Zhou D, Chen S et al (2016) Single-Image Crowd Counting via Multi-Column Convolutional Neural Network[C]. Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, pp 589-597

  30. Zhang Y, Lin H, Guan Y et al (2019) GAN image super-resolution reconstruction model with improved residual block and adversarial loss[J]. J Harbin Inst Technol 51(11):128–137

    Google Scholar 

  31. Zhao J, Wang X (2019) Vehicle-logo recognition based on modified HU invariant moments and SVM[J]. Multimed Tools Appl 78(1):75–97

    Article  Google Scholar 

  32. Zhao J, Wu H, Chen L (2017) Road Surface State Recognition Based on SVM Optimization and Image Segmentation Processing[J]. J Adv Transp 2017:1–21

    Google Scholar 

Download references

Acknowledgement

This work is supported by the National Key R&D Program of China (2019YFB1600200), National Natural Science Foundation of China (71871011, 71890972/71890970, 71621001), and the first batch of science and technology projects of Jingde Expressway (JD-202014).

Author information

Authors and Affiliations

  1. School of Traffic and Transportation, Beijing Jiaotong University, Beijing, 100044, China

    Jiandong Zhao, Zijian Li & Dongfeng Zhao

  2. Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Ministry of Transport, Beijing Jiaotong University, Beijing, 100044, China

    Jiandong Zhao

  3. Hebei Provincial Communication Planning and Design Institute, Shijiazhuang, 050000, China

    Wei Lei, Mingmin Han & Xiaoqing Hou

Authors
  1. Jiandong Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Lei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zijian Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dongfeng Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mingmin Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiaoqing Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiandong Zhao.

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

Zhao, J., Lei, W., Li, Z. et al. Detection of crowdedness in bus compartments based on ResNet algorithm and video images. Multimed Tools Appl 81, 4753–4780 (2022). https://doi.org/10.1007/s11042-021-11008-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11008-6

Keywords

Search

Navigation