Advertisement

Content-Based Motorcycle Counting for Traffic Management by Image Recognition

  • Tzung-Pei HongEmail author
  • Yu-Chiao Yang
  • Ja-Hwung Su
  • Chun-Hao Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11432)

Abstract

Over the past few decades, advanced technologies have increased the number of vehicles, including cars and motorcycles. Because of the large increase of vehicles, the traffic flow becomes more complex and the traffic accidents increase as rapidly. To decrease the number of traffic accidents, a number of studies has been made for how to manage the traffic flow. Especially for motorcycles, in this paper, we propose a method that counts the motorcycles by Convolutional Neural Network (CNN). To reveal the effectiveness of the proposed method, a set of experiments were conducted and the experimental results show the proposed method can bring out a good performance that provides a good support for traffic management systems.

Keywords

Motorcycle counting Deep learning Convolutional Neural Network Traffic management Video surveillance 

References

  1. 1.
  2. 2.
  3. 3.
  4. 4.
    Connie, T., Al-Shabi, M., Cheah, W.P., Goh, M.: Facial expression recognition using a hybrid cnnsift aggregator. In: Proceedings of International Workshop on Multi-disciplinary Trends in Artificial Intelligence (2017). [12]Google Scholar
  5. 5.
    Hu, Y., Huber, A., Anumula, J., Liu, S.: Overcoming the vanishing gradient problem in plain recurrent networks. In: Proceedings of 6th International Conference on Learning Representations (2018). [13]Google Scholar
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems (2012). [16]Google Scholar
  7. 7.
    McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943). [18]MathSciNetCrossRefGoogle Scholar
  8. 8.
    Mhaskar, H.N., Micchelli, C.A.: How to choose an activation function. In: Proceedings of the 6th International Conference on Neural Information Processing Systems (1993). [19]Google Scholar
  9. 9.
    Mukhtar, A., Tang, T.B.: Vision based motorcycle detection using hog features. In: Proceeding of 2015 IEEE International Conference on Signal and Image Processing Applications (2015). [20]Google Scholar
  10. 10.
    Silva, R., Aires, K., Santos, T., Abdala, K., Veras, R., Soares, A.: Automatic detection of motorcyclists without helmet. In: Proceeding of 2013 XXXIX Latin American Computing Conference (2013). [21]Google Scholar
  11. 11.
    Wen, X., Yuan, H., Song, C., Liu, W., Zhao, H.: An algorithm based on SVM ensembles for motorcycle recognition. In: Proceeding of 2007 IEEE International Conference on Vehicular Electronics and Safety (2007). [24]Google Scholar
  12. 12.
    Zhang, Y., et al.: Towards end-to-end speech recognition with deep convolutional neural networks. In: Interspeech, pp. 410–414 (2016). [26]Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tzung-Pei Hong
    • 1
    • 2
    Email author
  • Yu-Chiao Yang
    • 1
  • Ja-Hwung Su
    • 3
  • Chun-Hao Chen
    • 4
  1. 1.Department of Computer Science and Information EngineeringNational University of KaohsiungKaohsiungTaiwan
  2. 2.Department of Computer Science and EngineeringNational Sun Yat-sen UniversityKaohsiungTaiwan
  3. 3.Department of Information ManagementCheng Shiu UniversityKaohsiungTaiwan
  4. 4.Department of Computer Science and Information EngineeringTamkang UniversityTaipeiTaiwan

Personalised recommendations