Advertisement

Lightweight deep network for traffic sign classification

  • Jianming Zhang
  • Wei Wang
  • Chaoquan Lu
  • Jin Wang
  • Arun Kumar SangaiahEmail author
Article

Abstract

Deeper neural networks have achieved great results in the field of computer vision and have been successfully applied to tasks such as traffic sign recognition. However, as traffic sign recognition systems are often deployed in resource-constrained environments, it is critical for the network design to be slim and accurate in these instances. Accordingly, in this paper, we propose two novel lightweight networks that can obtain higher recognition precision while preserving less trainable parameters in the models. Knowledge distillation transfers the knowledge in a trained model, called the teacher network, to a smaller model, called the student network. Moreover, to improve the accuracy of traffic sign recognition, we also implement a new module in our teacher network that combines two streams of feature channels with dense connectivity. To enable easy deployment on mobile devices, our student network is a simple end-to-end architecture containing five convolutional layers and a fully connected layer. Furthermore, by referring to the values of batch normalization (BN) scaling factors towards zero to identify insignificant channels, we prune redundant channels from the student network, yielding a compact model with accuracy comparable to that of more complex models. Our teacher network exhibited an accuracy rate of 93.16% when trained and tested on the CIFAR-10 general dataset. Using the knowledge of our teacher network, we train the student network on the GTSRB and BTSC traffic sign datasets. Thus, our student model uses only 0.8 million parameters while still achieving accuracy of 99.61% and 99.13% respectively on both datasets. All experimental results show that our lightweight networks can be useful when deploying deep convolutional neural networks (CNNs) on mobile embedded devices.

Keywords

Convolutional neural networks Traffic sign classification Knowledge distillation Network pruning 

Notes

Funding information

This work was supported in part by the National Natural Science Foundation of China under Grant 61772454, Grant 61811530332, and Grant 61811540410; in part by the Scientific Research Fund of Hunan Provincial Education Department under Grant 16A008; in part by the "Double First-class" International Cooperation and Development Scientific Research Project of Changsha University of Science and Technology under Grant 2019IC34; in part by the Postgraduate Scientific Research Innovation Fund of Hunan Province under Grant CX2018B565; in part by the Postgraduate Training Innovation Base Construction Project of Hunan Province under Grant 2017-451-30; and in part by the Postgraduate Course Construction Fund of CSUST under Grant KC201611.

References

  1. 1.
    Wang J, Ju C, Gao Y, Sangaiah AK, Kim G (2018) A PSO based energy efficient coverage control algorithm for wireless sensor networks. Comput Mater Continua 56(3):433–446Google Scholar
  2. 2.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  3. 3.
    Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84CrossRefGoogle Scholar
  4. 4.
    Tu Y, Lin Y, Wang J, Kim JU (2018) Semi-supervised learning with generative adversarial networks on digital signal modulation classification. Comput Mater Continua 55(2):243–254Google Scholar
  5. 5.
    Zhang J, Lu C, Li X, Kim HJ, Wang J (2019) A full convolutional network based on DenseNet for remote sensing scene classification. Math Biosci Eng 16(5):3345–3367CrossRefGoogle Scholar
  6. 6.
    Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 1440–1448Google Scholar
  7. 7.
    Zhang J, Jin K, Sun J, Wang J, Sangaiah AK (2018) Spatial and semantic convolutional features for robust visual object tracking. Multimed Tools Appl.  https://doi.org/10.1007/s11042-018-6562-8. Accessed 19 Dec 2018
  8. 8.
    Wang N, Yeung DY (2013) Learning a deep compact image representation for visual tracking. In: Proceedings of the advances in neural information processing systems (NIPS), pp 809–817Google Scholar
  9. 9.
    Zhang J, Jin X, Sun J, Wang J, Li K (2019) Dual model learning combined with multiple feature selection for accurate visual tracking. IEEE Access 7:43956–43969CrossRefGoogle Scholar
  10. 10.
    Zeng D, Dai Y, Li F, Sherratt RS, Wang J (2018) Adversarial learning for distant supervised relation extraction. Comput Mater Continua 55:121–136Google Scholar
  11. 11.
    Severyn A, Moschitti A (2015) Learning to rank short text pairs with convolutional deep neural networks. In: Proceedings of the 38th International ACM Conference on Research and Development in information retrieval, pp 373–382Google Scholar
  12. 12.
    Wang G, Ren G, Wu Z, Zhao Y, Jiang LH (2013) A robust, coarse-to-fine traffic sign detection method. In: Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN), pp 754–758Google Scholar
  13. 13.
    Chen Y, Xu W, Zuo J, Yang K (2018) The fire recognition algorithm using dynamic feature fusion and IV-SVM classifier. Clust Comput.  https://doi.org/10.1007/s10586-018-2368-8. Accessed 19 Dec 2018
  14. 14.
    Chen Y, Xiong J, Xu W, Zuo J (2018) A novel online incremental and decremental learning algorithm based on variable support vector machine. Clust Comput.  https://doi.org/10.1007/s10586-018-1772-4. Accessed 19 Dec 2018
  15. 15.
    Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: Proceedings of the 2011 International Joint Conference on Neural Network (IJCNN), pp 2809–2813Google Scholar
  16. 16.
    Ciregan D, Meier U, Masci J, Schmidhuber J (2012) Multi-column deep neural network for traffic sign classification. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 3642–3649Google Scholar
  17. 17.
    Zeng Y, Xu X, Fang Y, Zhao K (2015) Traffic sign recognition using deep convolutional networks and extreme learning machine. In: Proceedings of International Conference on Intelligence Science and Big Data Engineering (IScIDE), pp 272–280Google Scholar
  18. 18.
    Jin J, Fu K, Zhang C (2014) Traffic sign recognition with hinge loss trained convolutional neural networks. IEEE Trans Intell Transp Syst 15:1991–2000CrossRefGoogle Scholar
  19. 19.
    Zeng Y, Xu X, Shen D, Fang Y (2017) Traffic sign recognition using kernel extreme learning machines with deep perceptual features. IEEE Trans Intell Transp Syst 18(6):1647–1653Google Scholar
  20. 20.
    Ngiam J, Coates A, Lahiri A, Prochnow B, Ng A (2011) On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML), pp 265–272Google Scholar
  21. 21.
    Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the advances in neural information processing systems (NIPS), pp 1097–1105Google Scholar
  22. 22.
    Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3th International Conference on Learning Representations (ICLR)Google Scholar
  23. 23.
    Denil M, Shakibi B, Dinh L, Ranzato M, De Freitas N (2013) Predicting parameters in deep learning. In: Proceedings of the advances in neural information processing systems (NIPS), pp 2148–2156Google Scholar
  24. 24.
    Denton E, Zaremba W, Bruna J, Lecun Y, Fergus R (2014) Exploiting linear structure within convolutional networks for efficient evaluation. In: Proceedings of the advances in neural information processing systems (NIPS), pp 1269–1277Google Scholar
  25. 25.
    Molchanov P, Tyree S, Karras T, Aila T, Kautz J (2016) Pruning convolutional neural networks for resource efficient inference. In: Proceedings of the 5th International Conference on Learning Representations (ICLR), pp 1–17Google Scholar
  26. 26.
    Zhu C, Han S, Mao H, Dally WJ (2017) Trained ternary quantization. In: Proceedings of the 5th international conference on learning representations (ICLR)Google Scholar
  27. 27.
    Hinton G, Vinyals O, Dean J (2014) Distilling the knowledge in a neural network. In: Proceedings of the advances in neural information processing systems (NIPS), pp 2644−2652Google Scholar
  28. 28.
    Huang G, Liu Z, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2261–2269Google Scholar
  29. 29.
    Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the international conference on machine learning (ICML), pp 448–456Google Scholar
  30. 30.
    Nair V, Hinton G (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML), pp 807–814Google Scholar
  31. 31.
    Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of international conference on learning representations, pp 1–15Google Scholar
  32. 32.
    Tai C, Xiao T, Zhang Y, Wang X, Weinan E (2015) Convolutional neural networks with low-rank regularization. https://arxiv.org/abs/1511.06067. Accessed 19 Dec 2018
  33. 33.
    He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1389–1397Google Scholar
  34. 34.
    Hu H, Peng R, Tai YW (2017) Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. In: Proceedings of international conference on learning representations (ICLR), pp 214–222Google Scholar
  35. 35.
    Liu Z, Li J, Shen Z, Huang G, Yan S, Zhang C (2017) Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 2755–2763Google Scholar
  36. 36.
    Matsubara S, Isayana H (2011) The German traffic sign recognition benchmark: a multi-class classification competition. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp 1453–1460Google Scholar
  37. 37.
    Mathias M, Timofte R, Benenson R, Van GL (2013) Traffic sign recognition-how far are we from the solution? In: Proceedings of the 2013 international joint conference on neural networks (IJCNN), pp 1–8Google Scholar
  38. 38.
    Krizhevsky A (2009) Learning multiple layers of features from tiny images. Technical Report TR–2009, University of Toronto. http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf. Accessed 19 Dec 2018
  39. 39.
    Szegedy C, Liu W, Jia Y, et al (2015) Going deeper with convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1–9Google Scholar
  40. 40.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR)Google Scholar
  41. 41.
    Arcos-Garcia A, Alvarez-Garcia J, Soria-Morillo LM (2018) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158–165CrossRefGoogle Scholar
  42. 42.
    Yu Y, Li J, Wen C, Guan H, Luo H, Wang C (2016) Bag-of-visual-phrases and hierarchical deep models for traffic sign detection and recognition in mobile laser scanning data. ISPRS J Photogramm Remote Sens 113:106–123CrossRefGoogle Scholar
  43. 43.
    Jurisic F, Filkovic I, Kalafatic Z (2011) Multiple-dataset traffic sign classification with OneCNN. In: Proceedings of 2015 3rd IAPR Asian conference on pattern recognition, Kuala Lumpur, pp 614–618Google Scholar

Copyright information

© Institut Mines-Télécom and Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangshaChina
  2. 2.Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangshaChina
  3. 3.School of Computer Science and EngineeringVellore Institute of TechnologyVelloreIndia

Personalised recommendations