Advertisement

Intelligent Traffic System Based on Neural Network

  • Jian ZhaoEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 772)

Abstract

Speed measurement is an important part of the traffic system. In general, the speed measurement system needs to be used in conjunction with a camera system to accomplish speeding and recording of passing vehicles. However, due to the complexity of the environment such as weather and light, the accuracy of the speed and recording is reduced. Traffic speed system based on neural network uses vehicle license plate as characteristic maps, it uses a neural network with improved parameters to identify the license plate and mark the vehicle. Then the monocular vision technology is used to measure the distance of the vehicle running at the unit frame rate, so as to calculate the speed of the vehicle. This system reduces the false detection rate of the license plate, and completes the measurement and record of the speed. In a large number of experiments, the system confirmed that the maximum false positive rate is 2.6%. The system can process 25 images in one second which meet the requirements of real-time and accuracy.

Keywords

Traffic velocity measurement Neural network Deep learning Vision technology 

References

  1. 1.
    Michels, J., Saxena, A., Ng, A.Y.: High speed obstacle avoidance using monocular vision and reinforcement learning. In: International Conference, DBLP, pp. 593–600 (2005)Google Scholar
  2. 2.
    Qiu, J.H., Shen, M.X., Cong, J.H., et al.: Monocular vision technique based real-time location of fire-point in forest. J. Zhejiang For. Coll. 651–658 (2010)Google Scholar
  3. 3.
    Puig, L., Guerrero, J.J.: Self-location from monocular uncalibrated vision using reference omniviews. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5216–5221. IEEE (2009)Google Scholar
  4. 4.
    Li, G., Ji, C., Gu, B., et al.: Recognition and location of oscillating fruit based on monocular vision and ultrasonic testing. Trans. Chin. Soc. Agric. Mach. (2015)Google Scholar
  5. 5.
    Yu, N., Huang, C., Lin, J.: Target location and ranging based on monocular vision robot. Comput. Meas. Control, 2654–2639 (2012)Google Scholar
  6. 6.
    Marmoiton, F., Collange, F., Derutin, J.P.: Location and relative speed estimation of vehicles by monocular vision. In: Proceedings of the IEEE Intelligent Vehicles Symposium, IV 2000, pp. 227–232. IEEE (2000)Google Scholar
  7. 7.
    Agostino, M.: Closed-Form solution for attitude and speed determination by fusing monocular vision and inertial sensor measurements. In: IEEE International Conference on Robotics and Automation, pp. 4538–4545. IEEE (2011)Google Scholar
  8. 8.
    Ji, Y., Shi, Z., Ren, J., et al.: 3D velocity measurement of high-speed rotating sphere based on the monocular vision servo system (2016)Google Scholar
  9. 9.
    Qu, Y., Yang, H.: High-speed measurement of nozzle swing angle of rocket engine based on monocular vision (2015)Google Scholar
  10. 10.
    Nijhuis, J.A.G., Ter Brugge, M.H., Helmholt, K.A., et al.: Car license plate recognition with neural networks and fuzzy logic. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 5, pp. 2232–2236. IEEE Xplore (1995)Google Scholar
  11. 11.
    Zhao, Z.H., Yang, S.P., Ma, Z.Q.: License plate character recognition based on convolutional neural network LeNet-5. J. Syst. Simul., 638–641 (2010)Google Scholar
  12. 12.
    Li, G., Zeng, R., Lin, L. Research on vehicle license plate location based on neural networks. In: International Conference on Innovative Computing, Information and Control, pp. 174–177. IEEE Computer Society (2006)Google Scholar
  13. 13.
    Rafique, M.A., Pedrycz, W., Jeon, M.: Vehicle license plate detection using region-based convolutional neural networks. Soft Comput., 1–12 (2017)Google Scholar
  14. 14.
    Masood, S.Z., Shu, G., Dehghan, A., et al.: License plate detection and recognition using deeply learned convolutional neural networks (2017)Google Scholar
  15. 15.
    Yu, N., Jiao, P., Zheng, Y.: Handwritten digits recognition base on improved LeNet5. In: Control and Decision Conference, pp. 4871–4875. IEEE (2015)Google Scholar
  16. 16.
    Dang, Q., Miao, M.A., Chen, Y.: A traffic sign recognition algorithm based on the 2-level improved LeNet-5. J. Shaanxi Normal Univ. (2017)Google Scholar
  17. 17.
    El-Sawy, A., El-Bakry, H., Loey, M., et al.: CNN for handwritten Arabic digits recognition based on LeNet-5. In: Proceedings of the International Conference on Advanced Intelligent Systems and Informatics (2016, 2017)Google Scholar
  18. 18.
    Guo, J., Wang, X., Huang, J., et al.: A vision chip architecture for image recognition based on improved convolutional neural network. In: IEEE International Conference on Electron Devices and Solid-State Circuits, pp. 310–313. IEEE (2016)Google Scholar
  19. 19.
    Zhang, L., Zhu, Y.Q., Chen, G.: License plate recognition method based on convolutional neural network SLeNet_5. Inf. Technol. (2015)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Beijing Power Machinery InstituteBeijingChina

Personalised recommendations