Skip to main content
SpringerLink
Log in

Automated detection of helmet on motorcyclists from traffic surveillance videos: a comparative analysis using hand-crafted features and CNN

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

Abstract

The higher mortality rate in motorcycle accidents is attributed to negligence in wearing a helmet by two-wheeler riders. Identification of helmetless riders in real-time is an essential task to prevent the occurrence of such events. This paper presents an automated system to identify motorcyclists without a helmet from traffic surveillance videos in real-time. The problem becomes more challenging when computational resources are limited. We have compiled a custom dataset for developing an automated helmet detection algorithm. The proposed system uses a two-stage classifier to extract motorcycles from surveillance videos. Detected motorcycles are further fed to a helmet identification stage. We present two algorithms for classifying riders with and without a helmet, one based on hand-crafted features and the other based on deep convolutional neural network (CNN). Our experiments show that the proposed CNN model gives the best performance in terms of accuracy while the feature-based model gives faster detection. Most importantly, to ensure the light-weightiness of the proposed system all the computations are performed in CPUs only.

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

Similar content being viewed by others

References

  1. Bouwmans T (2012) Background subtraction for visual surveillance: a fuzzy approach. Handb Soft Comput Video Surveill 5:103–138

    Article  Google Scholar 

  2. Bouwmans T (2014) Traditional and recent approaches in background modeling for foreground detection: an overview. Comput Sci Rev 11:31–66

    Article  Google Scholar 

  3. Chen X, He F, Yu H (2019) A matting method based on full feature coverage. Multimed Tools Appl 78(9):11,173–11,201

    Article  Google Scholar 

  4. Chiranjeevi P, Sengupta S (2017) Interval-valued model level fuzzy aggregation-based background subtraction. IEEE Trans Cybern 47(9):2544–2555

    Article  Google Scholar 

  5. Chiu CC, Ku MY, Chen HT (2007) Motorcycle detection and tracking system with occlusion segmentation. In: 2007. WIAMIS’07. Eighth international workshop on Image analysis for multimedia interactive services. IEEE, pp 32–32

  6. Chiverton J (2012) Helmet presence classification with motorcycle detection and tracking. IET Intell Transp Syst 6(3):259–269

    Article  MathSciNet  Google Scholar 

  7. Cuevas C, Martinez R, Berjón D, Garcia N (2017) Detection of stationary foreground objects using multiple nonparametric background-foreground models on a finite state machine. IEEE Trans Image Process 26(3):1127–1142

    Article  MathSciNet  Google Scholar 

  8. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005. CVPR 2005. IEEE computer society conference on Computer vision and pattern recognition. IEEE, vol 1, pp 886–893

  9. Di Stefano L, Mattoccia S, Mola M (2004) A change-detection algorithm enabling intelligent background maintenance. In: International conference image analysis and recognition. Springer, pp 437–445

  10. Dillencourt MB, Samet H, Tamminen M (1992) A general approach to connected-component labeling for arbitrary image representations. J ACM (JACM) 39(2):253–280

    Article  MathSciNet  Google Scholar 

  11. e Silva RR, Aires K, de MS Veras R (2017) Detection of helmets on motorcyclists. Multimedia Tools and Applications 77:1–25

    Google Scholar 

  12. Fisher R, Perkins S, Walker A, Wolfart E (2003) Connected component labeling. website: http://homepages.inf.ed.ac.uk/rbf/HIPR2/label.htm

  13. Gupte S, Masoud O, Martin RF, Papanikolopoulos NP (2002) Detection and classification of vehicles. IEEE Trans Intell Transp Syst 3(1):37–47

    Article  Google Scholar 

  14. Haralick RM, Shanmugam K, et al. (1973) Textural features for image classification. IEEE Transactions on systems, man, and cybernetics SMC-3(6):610–621

    Article  Google Scholar 

  15. Huang SC (2011) An advanced motion detection algorithm with video quality analysis for video surveillance systems. IEEE Trans Circ Syst Video Technol 21(1):1–14

    Article  Google Scholar 

  16. https://www.techsciresearch.com/report/global-two-wheeler-market/1416.html/. Accessed: 2010-09-30

  17. Kim K, Chalidabhongse TH, Harwood D, Davis L (2004) Background modeling and subtraction by codebook construction. In: 2004 international conference on Image processing (ICIP). IEEE, vol 5, pp 3061–3064

  18. Krishnapuram B, Carin L, Figueiredo MA, Hartemink AJ (2005) Sparse multinomial logistic regression: Fast algorithms and generalization bounds. IEEE Trans Pattern Anal Mach Intell 27(6):957–968

    Article  Google Scholar 

  19. le Cessie S, van Houwelingen J (1992) Ridge estimators in logistic regression. Appl Stat 41(1):191–201

    Article  Google Scholar 

  20. Leelasantitham A, Wongseree W (2008) Detection and classification of moving thai vehicles based on traffic engineering knowledge. In: 2008. ITST 2008. 8th international conference on ITS Telecommunications. IEEE, pp 439–442

  21. Li X, Ng MK, Yuan X (2015) Median filtering-based methods for static background extraction from surveillance video. Numer Linear Algebra Appl 22 (5):845–865

    Article  MathSciNet  Google Scholar 

  22. McCarthy M, Walter L, Hutchins R, Tong R, Keigan M (2007) Comparative analysis of motorcycle accident data from ots and maids. Published Project Report PPR 168

  23. Mukhtar A, Tang TB (2015) Vision based motorcycle detection using hog features. In: 2015 IEEE international conference on Signal and image processing applications (ICSIPA). IEEE, pp 452–456

  24. Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recogn 29(1):51–59

    Article  Google Scholar 

  25. Organization WH (2018) Global status report on road safety 2018: Summary. Tech. rep., World Health Organization

  26. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. (2011) Scikit-learn: Machine learning in python. J Mach Learn Res 12(Oct):2825–2830

    MathSciNet  MATH  Google Scholar 

  27. Ramirez-Quintana JA, Chacon-Murguia MI (2015) Self-adaptive som-cnn neural system for dynamic object detection in normal and complex scenarios. Pattern Recogn 48(4):1137–1149

    Article  Google Scholar 

  28. Schölkopf B, Burges CJ, Smola AJ, et al. (1999) Advances in kernel methods: support vector learning. MIT Press, Cambridge

  29. Silva R, Aires K, Veras R, Santos T, Lima K, Soares A (2013) Automatic motorcycle detection on public roads. CLEI Electron J 16(3):4–4

    Article  Google Scholar 

  30. Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: 1999. IEEE computer society conference on Computer vision and pattern recognition. IEEE, vol 2, pp 246–252

  31. Teknomo K, Fernandez P (2015) Background image generation using boolean operations. arXiv:1510.00889

  32. Vishnu C, Singh D, Mohan CK, Babu S (2017) Detection of motorcyclists without helmet in videos using convolutional neural network. In: 2017 international joint conference on Neural networks (IJCNN). IEEE, pp 3036–3041

  33. Waranusast R, Bundon N, Timtong V, Tangnoi C, Pattanathaburt P (2013) Machine vision techniques for motorcycle safety helmet detection. In: 2013 28th international conference of Image and vision computing New Zealand (IVCNZ). IEEE, pp 35–40

  34. Wu H, Zhao J (2018) An intelligent vision-based approach for helmet identification for work safety. Comput Ind 100:267–277

    Article  Google Scholar 

  35. Yamamoto A, Iwai Y (2009) Real-time object detection with adaptive background model and margined sign correlation. In: Asian conference on computer vision. Springer, pp 65–74

  36. Yu H, He F, Pan Y (2018) A novel region-based active contour model via local patch similarity measure for image segmentation. Multimed Tools Appl 77 (18):24,097–24,119

    Article  Google Scholar 

  37. Yu H, He F, Pan Y (2019) A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation. Multimed Tools Appl 78 (9):11,779–11,798

    Article  Google Scholar 

  38. Zhang S, He F, Ren W, Yao J (2018) Joint learning of image detail and transmission map for single image dehazing. Vis Comput 35:1–12

    Google Scholar 

  39. Zhiwei H, Jilin L, Peihong L (2004) New method of background update for video-based vehicle detection. In: 2004. Proceedings. the 7th international IEEE conference on Intelligent transportation systems. IEEE, pp 580–584

  40. Zivkovic Z, Van Der Heijden F (2006) Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recogn Lett 27(7):773–780

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Computer vision Lab, College of Engineering Trivandrum, Kerala, India

    Linu Shine & Jiji C. V.

Authors
  1. Linu Shine
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiji C. V.
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Linu Shine.

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

Shine, L., C. V., J. Automated detection of helmet on motorcyclists from traffic surveillance videos: a comparative analysis using hand-crafted features and CNN. Multimed Tools Appl 79, 14179–14199 (2020). https://doi.org/10.1007/s11042-020-08627-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-08627-w

Keywords

Search

Navigation