Abstract
Traffic signal recognition is one of the critical points of the technology of intelligent driving. The research on traffic signal recognition has lasted for decades and attracted more and more research attentions from the research and industry communities. Most of the previous work are based on the vision clues to deal with the problem of traffic signal recognition, while in this paper we propose a novel method which is an integration of prior signal position knowledge and the computer vision based on object detection. With prior knowledge of signal position, the detection area can be reduced and the efficiency of signal recognition is increased significantly. Experiments are conducted on the real-world dataset, and the experimental results show that compared with the previous work and the state-of-the-arts, our method achieves the best performance and satisfies the requirements of signal recognition in intelligent driving.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goetz, J., Zittlau, D., Happe, J.: Advanced driver assistance systems—enhancement of safety and comfort. Autotechnology 6(6), 34–38 (2006)
Lin, F., Lai, Y., Lin, L., Yuan, Y.: A traffic sign recognition method based on deep visual feature. In: 2016 Progress in Electromagnetic Research Symposium (PIERS), Shanghai, 8–11 August, pp. 2247–2250 (2016)
Lai, Y., Wang, N., Yang, Y., Lin, L.: Traffic signs recognition and classification based on deep feature learning. In: 7th International Conference on Pattern Recognition Applications and Methods (ICPRAM), Madeira, Portugal, 16–18 January, pp. 622–629 (2018)
Zhang, G., Lin, F., Lin, L.: A novel method of front vehicle recognition. In: 2016 Progress in Electromagnetic Research Symposium (PIERS), Shanghai, 8–11 August, pp. 2126–2130 (2016)
Park, J.H., Jeong, C.: Real-time signal light detection. In: 2nd International Conference on Future Generation Communication and Networking Symposia, pp. 139–142. IEEE (2008)
Omachi, M., Omachi, S.: Traffic light detection with color and edge information. In: 2nd International Conference on Computer Science and Information Technology, pp. 284–287. IEEE (2009)
Gong, J., Jiang, Y., Xiong, G., et al.: The recognition and tracking of traffic lights based on color segmentation and Camshift for intelligent vehicles. In: Intelligent Vehicles Symposium (IV), pp. 431–435, IEEE (2010)
Bradski, G.R.: Computer vision face tracking for use in a perceptual user interface. Intel Technol. J. Q2, 214–219 (1998)
John, V., Yoneda, K., Qi, B., et al.: Traffic light recognition in varying illumination using deep learning and saliency map. In: 17th International Conference on Intelligent Transportation Systems (ITSC), pp. 2286–2291. IEEE (2014)
Fairfield, N., Urmson, C.: Traffic light mapping and detection. In: International Conference on Robotics and Automation (ICRA), pp. 5421–5426. IEEE (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)
Henriques, J.F., Caseiro, R., Martins, P., et al.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)
Su, C.H., Chiu, H.S., Hsieh, T.M.: An efficient image retrieval based on HSV color space. In: 2011 International Conference on Electrical and Control Engineering (ICECE), pp. 5746–5749. IEEE (2011)
Recky, M., Leberl, F.: Windows detection using k-means in CIE-lab color space. In: 20th International Conference on Pattern Recognition (ICPR), pp. 356–359. IEEE (2010)
Acknowledgement
This work is supported by National Science Foundation of China 61373106.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Yu, Y., Lai, Y., Wang, H., Lin, L. (2018). Traffic Signal Recognition with a Priori Analysis of Signal Position. In: Moreno GarcÃa-Loygorri, J., Pérez-Yuste, A., Briso, C., Berbineau, M., Pirovano, A., Mendizábal, J. (eds) Communication Technologies for Vehicles. Nets4Cars/Nets4Trains/Nets4Aircraft 2018. Lecture Notes in Computer Science(), vol 10796. Springer, Cham. https://doi.org/10.1007/978-3-319-90371-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-90371-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-90370-5
Online ISBN: 978-3-319-90371-2
eBook Packages: Computer ScienceComputer Science (R0)