Abstract
The driver fatigue detection method based on human eye feature information has the advantages, such as non-invasion, low cost, natural interaction and so on, which has been widely favored. However, in the actual detection process, the driver’s face will be shaken due to various factors, and there will be motion blur, which will cause misjudgment and missed judgment on the fatigue driving detection. Therefore, this paper designs a method based on CNN convolutional neural network to detect human key points, then uses Kalman filter to track human eyes, eliminates jitter interference, and greatly improves the accuracy of fatigue detection. The experimental results show that the proposed method can track the human eyes in real time and has high accuracy and robustness.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cristinacce, D., Cootes, T.: Feature detection and tracking with constrained local models. In: Proceedings of the British Machine Vision Conference. BMVA, Edinburgh, UK, pp. 929–938 (2006)
Peng, N.S., Yang, J., Zhou, D.K.: Study on Bhattacharyya coefficients within mean-shift framework and its application. Soft Comput. Fusion Found. Methodol. Appl. 10(12), 1127–1134 (2006)
Shi, H.W., Xia, L.M.: Human eye tracking based on Mean Shift algorithm and particle filter. Comput. Eng. Appl. 42(19), 26–28 (2006)
Zhang, Y.Y., Wang, H.J., Huang, Y.D., et al.: Pedestrian target tracking method based on Meanshift and particle filter. Comput. Modernization 3, 40–43 (2012)
Dong, W.H., Wu, X.J., Qu, P.S.: Human eye tracking based on rule and Kalman filter. Comput. Eng. Sci. 28(11), 27–29 (2006)
Chen, Y.Q., Luo, D.Y.: Real-time tracking of human eyes based on Kalman filtering and Mean Shift algorithm. Pattern Recog. Artif. Intell. 17(2), 173–177 (2004)
Comaniciu, D., Ramesh, V.: Mean shift and optimal prediction for efficient object tracking. In: International Conference on Image Processing. CiteSeer (2000). https://doi.org/10.1109/ICIP.2000.899297
Breitbart, Y., Garofalakis, M., Martin, C., et al.: Topology discovery in heterogeneous IP networks. In: Proceedings of IEEE INFOCOM, vol. 1, pp. 265–274 (2000)
Deng, Y.H.: Multi-target tracking based on decoupled de-biasing measurement Kalman filter algorithm. In: Proceedings of 2016 IEEE Chinese Guidance, Navigation and Control Conference (IEEE CGNCC 2016). China Aviation Society Guidance, Navigation and Control Branch Key Laboratory of Integrated Aircraft Control Technology, Nanjing Branch of IEEE Control System Association: China Aviation Society, no. 6, pp. 2859–2864 (2016)
Singh, A., Minsker, B.S., Bajcsy, P.: Image-based machine learning for reduction of user fatigue in an interactive model calibration system. J. Comput. Civ. Eng. 24(3), 241–251 (2010)
Jiang, T.: An image classification algorithm based on multidomain convolution neural network. In: Science and Engineering Research Center. Proceedings of 2017 2nd International Conference on Wireless Communication and Network Engineering (WCNE 2017), no. 6, pp. 370–375 (2017)
Li, X.: Airplane detection using convolutional neural networks in a coarse-to-fine manner. In: IEEE Beijing Section, Global Union Academy of Science and Technology, Chongqing Global Union Academy of Science and Technology. Proceedings of 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2017), no. 5, pp. 270–274 (2017)
Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 9, no. 13, pp. 3476–3483 (2013)
Khashirunnisa, S., Chand, B.K., Kumari, B.L.: Performance analysis of Kalman filter, fuzzy Kalman filter and wind driven optimized Kalman filter for tracking applications. In: 2nd International Conference on Communication Control and Intelligent Systems (CCIS), Mathura, pp. 170–174 (2016)
Acknowledgments
We would like to acknowledge the support of the Guangzhou Innovation and Entrepreneurship Leading Team Project under grant CXLJTD-201609.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer-Verlag GmbH Germany, part of Springer Nature
About this chapter
Cite this chapter
Pan, Z., Liu, R., Zhang, M. (2019). Human Eye Tracking Based on CNN and Kalman Filtering. In: Pan, Z., Cheok, A., Müller, W., Zhang, M., El Rhalibi, A., Kifayat, K. (eds) Transactions on Edutainment XV. Lecture Notes in Computer Science(), vol 11345. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-59351-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-662-59351-6_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-59350-9
Online ISBN: 978-3-662-59351-6
eBook Packages: Computer ScienceComputer Science (R0)