In urban environment the trusted traffic lights identification and classification is very important for automated driving vehicles. In urban driving presently there is no such systems that has to become aware of dependable traffic lights in real time and we can find the traffic lights in automated vehicles without map based information and enough distance require for regular surface in urban driving. Here we suggest a complete system made up of traffic light detector, tracker, and classifier based on deep learning, stereo vision, and vehicle odometer which become aware of traffic lights in real time The first is a precisely marked traffic signals data sets contains 5000 guiding pictures and 8335 motion pictures for development. Tiny traffic signals dataset is distributed by Bosch Company is used as a basic tool. The traffic signal identification which works at 10 frames per second on 1280*720 images is the second achievement. Third achievement is a traffic signal which identifies utilizes stereo vision and odometer of vehicles to calculate the moment computation of traffic signals.

Convolution Neural Network , Odometer, Stereo vision, , Traffic Light, GPS Detector, AdaBoost Algorithm, RGB Conversion, Pixels, Grey scale Images, Dimensional Matrix

[1] C. Wang, T. Jin, M. Yang, and B. Wang, “Robust and real-time traffic lights recognition in complex urban environments,” International Journal of Computational Intelligence Systems, vol. 4, no. 6, pp. 1383–1390, 2011.

[2] R. de Charette and F. Nashashibi, “Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates,” in Intelligent Vehicles Symposium, 2009 IEEE. IEEE, 2009, pp. 358–363.

[3] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolution neural networks,” in Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States., 2012, pp.1106–1114.

[4] V. Haltakov, J. Mayor, C. Unger, and S. Ilic, “Semantic segmentation based traffic light detection at day and at night,” in German Conferenceon Pattern Recognition. Springer, 2015, pp. 446–457.

[5] M. Diaz-Cabrera, P. Cerri, and P. Medici, “Robust real-time traffic light detection and distance estimation using a single camera,” ExpertSystems with Applications, vol. 42, no. 8, pp. 3911–3923, 2015.

[6] M. P. Philipsen, M. B. Jensen, A. Møgelmose, T. B. Moeslund, and M. M. Trivedi, “Traffic light detection: a learning algorithm and evaluations on challenging dataset,” in Intelligent TransportationSystems (ITSC), 2015 IEEE 18th International Conference on. IEEE, 2015, pp. 2341–2345.

[7] G. Siogkas, E. Skodras, and E. Dermatas, “Traffic lights detection in adverse conditions color, symmetry and spatiotemporal information. “in VISAPP (1), 2012, pp. 620M-627.

[8] N. Fairfield and C. Urmson, “Traffic light mapping and detection, “in Robotics and Automation(ICRA), 2011 IEEE international conference on. IEEE, 2011, pp. 5421-5426.

[9] M. Diaz-Cabrera, P.Cerri, and J. Sanchez-Medina, “Suspended Traffic lights detection and distance estimation using color features”, in 2012 15th international IEEE conference on Intelligent Transportation Systems. IEEE, 2012, pp. 1315-1320.