A Traffic Light Recognition Device

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 738)

Abstract

Traffic lights detection and recognition research has grown every year. Time is coming when autonomous vehicle can navigate in urban roads and streets and intelligent systems aboard those cars would have to recognize traffic lights in real time. This article proposes a traffic light recognition (TLR) device prototype using a smartphone as camera and processing unit that can be used as a driver assistance. A TLR device has to be able to visualize the traffic scene from inside of a vehicle, generate stable images, and be protected from adverse conditions. To validate this layout prototype, a dataset was built and used to test an algorithm that uses an adaptive background suppression filter (AdaBSF) and Support Vector Machines (SVMs) to detect traffic lights. The application of AdaBSF and subsequent classification with SVM to the dataset achieved 100% precision rate and recall of 65%. Road testing shows that the TLR device prototype meets the requirements to be used as a driver assistance device.

Keywords

Traffic light detection and recognition Support vector machines Computer vision Expert systems 

Notes

Acknowledgements

The authors thank CAPES and FAPITEC-SE for the financial support [Edital CAPES/FAPITEC/SE No 11/2016—PROEF, Processo 88887.160994/2017-00]. The authors also thank FAPITEC-SE for granting a graduate scholarship to Thiago Almeida and CNPq for granting a productivity scholarship to Hendrik Macedo [DT-II, Processo 310446/2014-7].

References

  1. 1.
    CET - Companhia de Engenharia de Tráfego. (2015) Análise da mortalidade ocorrida por acidentes de trânsito em agosto e setembro de 2016. Acesso em: 09 ago (2017). Online Available: http://www.cetsp.com.br/media/523410/parcial2016.pdf
  2. 2.
    Z. Shi, Z. Zou, C. Zhang, Real-time traffic light detection with adaptative background suppression filter. IEEE Trans. Intell. Transp. Syst. 17(3), 690–700 (2016)CrossRefGoogle Scholar
  3. 3.
    M. Weber, P. Wolf, J. M. Zöllner, Deeptlr: a single deep convolutional network for detection and classification of traffic lights, in 2016 IEEE Intelligent Vehicles Symposium (IV), June (2016), pp. 342–348Google Scholar
  4. 4.
    V. John, L. Zheming, S. Mita, Robust traffic light and arrow detection using optimal camera parameters and GPS-based priors, in 2016 Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), July (2016), pp. 204–208Google Scholar
  5. 5.
    V. John, K. Yoneda, Z. Liu, S. Mita, Saliency map generation by the convolutional neural network for real-time traffic light detection using template matching. IEEE Trans. Comput. Imaging 1(3), 159–173 (2015)Google Scholar
  6. 6.
    V. John, K. Yoneda, B. Qi, Z. Liu, S. Mita, Traffic light recognition in varying illumination using deep learning and saliency map, in 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), Oct (2014), pp. 2286–2291Google Scholar
  7. 7.
    Z. Wang, Z. Bi, C. Wang, L. Lin, H. Wang, Traffic lights recognition based on PCANET, in 2015 Chinese Automation Congress (CAC), Nov (2015), pp. 559–564Google Scholar
  8. 8.
    M.P. Philipsen, M.B. Jensen, A. Møgelmose, T.B. Moeslund, M.M. Trivedi, Traffic light detection: a learning algorithm and evaluations on challenging dataset, in 2015 IEEE 18th International Conference on Intelligent Transportation Systems, Sept (2015), pp. 2341–2345Google Scholar
  9. 9.
    S. Kim, E. Jang, S. Hyun, D.S. Han, Real time object detection based on saliency map, in 2016 IEEE International Conference on Consumer Electronics (ICCE), Jan (2016), pp. 534–535Google Scholar
  10. 10.
    T. Almeida, N. Vasconcelos, A. Benicasa, H. Macedo, Fuzzy model applied to the recognition of traffic lights signals, in 2016 8th Euro American Conference on Telematics and Information Systems (EATIS), April (2016), pp. 1–4Google Scholar
  11. 11.
    T. Almeida, N. Vasconcelos, A. Benicasa, Framework para detecção de semáforos baseado em atenção visual, in Conference on Graphics, Patterns and Images, 28. (SIBGRAPI), Salvador (2015)Google Scholar
  12. 12.
    Y. Ji, M. Yang, Z. Lu, C. Wang, Integrating visual selective attention model with hog features for traffic light detection and recognition, in 2015 IEEE Intelligent Vehicles Symposium (IV), June (2015), pp. 280–285Google Scholar
  13. 13.
    Y. Zhou, Z. Chen, X. Huang, A system-on-chip FPGA design for real-time traffic signal recognition system, in 2016 IEEE International Symposium on Circuits and Systems (ISCAS), May (2016), pp. 1778–1781Google Scholar
  14. 14.
    Z. Chen, X. Huang, Accurate and reliable detection of traffic lights using multiclass learning and multiobject tracking. IEEE Intell. Transp. Syst. Mag. 8(4), 28–42 (2016)CrossRefGoogle Scholar
  15. 15.
    Y. Zhang, J. Xue, G. Zhang, Y. Zhang, N. Zheng, A multi-feature fusion based traffic light recognition algorithm for intelligent vehicles, in Proceedings of the 33rd Chinese Control Conference, July (2014), pp. 4924–4929Google Scholar
  16. 16.
    D.H. Widyantoro, K.I. Saputra, Traffic lights detection and recognition based on color segmentation and circle hough transform, in 2015 International Conference on Data and Software Engineering (ICoDSE), Nov (2015), pp. 237–240Google Scholar
  17. 17.
    Y.T. Chiu, D.Y. Chen, J.W. Hsieh, Real-time traffic light detection on resource-limited mobile platform, in 2014 IEEE International Conference on Consumer Electronics - Taiwan, May (2014), pp. 211–212Google Scholar
  18. 18.
    M. Omachi, S. Omachi, Detection of traffic light using structural information, in IEEE 10th International Conference on Signal Processing Proceedings, Oct (2010), pp. 809–812Google Scholar
  19. 19.
    S. Sooksatra, T. Kondo, Red traffic light detection using fast radial symmetry transform, in 2014 11th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), May (2014), pp. 1–6Google Scholar
  20. 20.
    G. Trehard, E. Pollard, B. Bradai, F. Nashashibi, Tracking both pose and status of a traffic light via an interacting multiple model filter, in 17th International Conference on Information Fusion (FUSION), July (2014), pp. 1–7Google Scholar
  21. 21.
    F. Oniga, S. Prodan, S. Nedevschi, Traffic light detection on mobile devices, in 2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), Sept (2015), pp. 287–292Google Scholar
  22. 22.
    Y. Jie, C. Xiaomin, G. Pengfei, X. Zhonglong, A new traffic light detection and recognition algorithm for electronic travel aid, in 2013 Fourth International Conference on Intelligent Control and Information Processing (ICICIP), June (2013), pp. 644–648Google Scholar
  23. 23.
    J. M. Borrmann, F. Haxel, D. Nienhüser, A. Viehl, J. M. Zöllner, O. Bringmann, W. Rosenstiel, Stellar - a case-study on systematically embedding a traffic light recognition, in 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), Oct (2014), pp. 1258–1265Google Scholar
  24. 24.
    W. Zong, Q. Chen, Traffic light detection based on multi-feature segmentation and online selecting scheme, in 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Oct (2014), pp. 204–209Google Scholar
  25. 25.
    S. Sathiya, M. Balasubramanian, D.V. Priya, Real time recognition of traffic light and their signal count-down timings, in International Conference on Information Communication and Embedded Systems (ICICES2014), Feb (2014), pp. 1–6Google Scholar
  26. 26.
    J. Gong, Y. Jiang, G. Xiong, C. Guan, G. Tao, H. Chen, The recognition and tracking of traffic lights based on color segmentation and camshift for intelligent vehicles, in 2010 IEEE Intelligent Vehicles Symposium, June (2010), pp. 431–435Google Scholar
  27. 27.
    X. Shi, N. Zhao, Y. Xia, Detection and classification of traffic lights for automated setup of road surveillance systems. Multimed. Tools Appl. 75(20), 12547–12562 (2016). Online Available: http://dx.doi.org/10.1007/s11042-014-2343-1 CrossRefGoogle Scholar
  28. 28.
    M. Michael, M. Schlipsing, Extending traffic light recognition: efficient classification of phase and pictogram, in 2015 International Joint Conference on Neural Networks (IJCNN), July (2015), pp. 1–8.Google Scholar
  29. 29.
    M. Salarian, A. Manavella, R. Ansari, A vision based system for traffic lights recognition, in 2015 SAI Intelligent Systems Conference (IntelliSys), Nov (2015), pp. 747–753Google Scholar
  30. 30.
    C. Jang, C. Kim, D. Kim, M. Lee, M. Sunwoo, Multiple exposure images based traffic light recognition, in 2014 IEEE Intelligent Vehicles Symposium Proceedings, June (2014), pp. 1313–1318Google Scholar
  31. 31.
    Q. Chen, Z. Shi, Z. Zou, Robust and real-time traffic light recognition based on hierarchical vision architecture, in 2014 7th International Congress on Image and Signal Processing, Oct (2014), pp. 114–119Google Scholar
  32. 32.
    Y.-C. Chung, J.-M. Wang, S.-W. Chen, A vision-based traffic light detection system at intersections. J. Natl. Taiwan Norm. Univ. Math. Sci. Technol. 47, 67–86 (2002)Google Scholar
  33. 33.
    A. Almagambetov, S. Velipasalar, A. Baitassova, Mobile standards-based traffic light detection in assistive devices for individuals with color-vision deficiency. IEEE Trans. Intell. Transp. Syst. 16(3), 1305–1320 (2015)CrossRefGoogle Scholar
  34. 34.
    J. Balcerek, A. Konieczka, T. Marciniak, A. D ąbrowski, K. Maćkowiak, K. Piniarski, Automatic detection of traffic lights changes from red to green and car turn signals in order to improve urban traffic, in 2014 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Sept (2014), pp. 110–115.Google Scholar
  35. 35.
    Z. Cai, Y. Li, M. Gu, Real-time recognition system of traffic light in urban environment, in 2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications, July (2012), pp. 1–6Google Scholar
  36. 36.
    M. Omachi, S. Omachi, Traffic light detection with color and edge information, in 2009 2nd IEEE International Conference on Computer Science and Information Technology, Aug (2009), pp. 284–287Google Scholar
  37. 37.
    J. Choi, B.T. Ahn, I.S. Kweon, Crosswalk and traffic light detection via integral framework, in The 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, Jan (2013), pp. 309–312Google Scholar
  38. 38.
    B. Fan, W. Lin, X. Yang, An efficient framework for recognizing traffic lights in night traffic images, in 2012 5th International Congress on Image and Signal Processing, Oct (2012), pp. 832–835Google Scholar
  39. 39.
    R. de Charette, F. Nashashibi, Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates, in 2009 IEEE Intelligent Vehicles Symposium, June (2009), pp. 358–363Google Scholar
  40. 40.
    J. Levinson, J. Askeland, J. Dolson, S. Thrun, Traffic light mapping, localization, and state detection for autonomous vehicles, in 2011 IEEE International Conference on Robotics and Automation, May (2011), pp. 5784–5791Google Scholar
  41. 41.
    S. Mascetti, D. Ahmetovic, A. Gerino, C. Bernareggi, M. Busso, A. Rizzi, Robust traffic lights detection on mobile devices for pedestrians with visual impairment. Comput. Vis. Image Underst. 148(C), 123–135 (2016). Online Available: https://doi.org/10.1016/j.cviu.2015.11.017 CrossRefGoogle Scholar
  42. 42.
    A.E. Gomez, F.A.R. Alencar, P.V. Prado, F.S. Osório, D.F. Wolf, Traffic lights detection and state estimation using hidden Markov models, in 2014 IEEE Intelligent Vehicles Symposium Proceedings, June (2014), pp. 750–755Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Thiago Almeida
    • 1
  • Hendrik Macedo
    • 1
  • Leonardo Matos
    • 1
  1. 1.Programa de Pós-Graduação em Ciência da Computação - PROCCUniversidade Federal de Sergipe - UFSSão CristóvãoBrazil

Personalised recommendations