Abstract
Traffic signs are a key constituent of the road network and prove to be very useful for warning and guiding the drivers. In intelligent transport systems, traffic sign recognition (TSR) is indispensable for autonomous driving. However, due to the complex outdoor environment, real-time recognition of traffic signs is much more challenging in comparison with many other pattern recognition tasks. Convolutional neural networks (CNNs) have an exceptional capability of recognizing patterns and are one of the most popular deep learning techniques. Finding the optimal configuration of a CNN for a task is a major challenge and is an active area of research. Genetic algorithm (GA) is a meta-heuristic approach well-known for its optimization power. In this paper, we propose a novel deep learning technique based on the concept of domain transfer learning for the recognition of traffic signs. This technique utilizes a newly proposed variant of the GA for finding the optimal values of the number of epochs and the learning rate parameter for each layer of the pre-trained CNN model (VGG-16). To examine the effectiveness of our technique, we apply it to the following two benchmark datasets of TSR: Belgium Traffic Sign Classification (BTSC) dataset and Chinese Traffic Sign Dataset (TT100K). The results indicate that our model outperforms all the existing approaches applied to these datasets and gives a new benchmark of the recognition accuracies of 99.16% for the BTSC and 96.28% for the TT100K datasets, thus establishing the robustness of our model.
References
Lu Y, Yi S, Zeng N, Liu Y, Zhang Y (2017) Identification of rice diseases using deep convolutional neural networks. Neurocomputing 267:378–384. https://doi.org/10.1016/j.neucom.2017.06.023
Zhang P, Niu X, Dou Y, Xia F (2017) Airport detection on optical satellite images using deep convolutional neural networks. IEEE Geosci Remote Sens Lett 14(8):1183–1187. https://doi.org/10.1109/LGRS.2017.2673118
Roth HR, Lee CT, Shin HC, Seff A, Kim L, Yao J, Lu L, Summers RM (2015) Anatomy-specific classification of medical images using deep convolutional nets. In: IEEE 12th ISBI, pp 101–104. http://doi.org/10.1109/ISBI.2015.7163826
Li J, Zhang Z, He H (2017) Hierarchical convolutional neural networks for EEG-based emotion recognition. Cogn Comput. https://doi.org/10.1007/s12559-017-9533-x
Lopes UK, Valiati JF (2017) Pre-trained convolutional neural networks as feature extractors for tuberculosis detection. Comput Biol Med. https://doi.org/10.1016/j.compbiomed.2017.08.001
Phan HTH, Kumar A, Kim J, Feng D (2016) Transfer learning of a convolutional neural network for HEp-2 cell image classification. In: IEEE 13th ISBI, pp 1208–1211. https://doi.org/10.1109/ISBI.2016.7493483
Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11–26. https://doi.org/10.1016/j.neucom.2016.12.038
Basagoiti MBR, Rodriguez IRV (2016) A modified genetic algorithm applied to the elevator dispatching problem. Soft Comput. https://doi.org/10.1007/s00500-015-1718-1
Hsu C, Cho H (2015) A genetic algorithm for the maximum edge-disjoint paths problem. Neurocomputing. https://doi.org/10.1016/j.neucom.2012.10.046
Shih CC, Horng MF, Pan TS, Pan JS, Chen CY (2016) A genetic-based effective approach to path-planning of autonomous underwater glider with upstream-current avoidance in variable oceans. Soft Computing. https://doi.org/10.1007/s00500-016-2122-1
Goldberg D (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading
Mishra A, Shukla A (2017) Mathematical analysis of the cumulative effect of novel ternary crossover operator and mutation on probability of survival of a schema. Theoret Comput Sci 666:1–11. https://doi.org/10.1016/j.tcs.2016.07.035
Uzor CJ, Gongora M, Coupland S, Passow BN (2016) Adaptive-mutation compact genetic algorithm for dynamic environments. Soft Comput 8:3097–3115. https://doi.org/10.1007/s00500-016-2195-x
Qiongbing Z, Lixin D (2016) A new crossover mechanism for genetic algorithms with variable-length chromosomes for path optimization problems. Expert Syst Appl 60:183–189. https://doi.org/10.1016/j.eswa.2016.04.005
Banerjee A (2013) A novel probabilistically-guided context-sensitive crossover operator for clustering. Swarm Evol Comput 13:47–62. https://doi.org/10.1016/j.swevo.2013.05.007
Mishra A, Shukla A (2018) Mathematical analysis of schema survival for genetic algorithms having dual mutation. Soft Comput 22(6):1763–1771. https://doi.org/10.1007/s00500-017-2650-3
Hu W, Zhuo Q, Zhang C, Li J (2017) Fast branch convolutional neural network for traffic sign recognition. IEEE Intell Transp Syst Mag 9(3):114–126. https://doi.org/10.1109/MITS.2017.2709780
Li Y, Møgelmose A, Trivedi MM (2016) Pushing the “Speed Limit”: high-accuracy US traffic sign recognition with convolutional neural networks. IEEE Trans Intell Veh 1(2):167–176. https://doi.org/10.1109/TIV.2016.2615523
Arcos-García Á, Álvarez-García JA, Soria-Morillo LM (2018) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158–165. https://doi.org/10.1016/j.neunet.2018.01.005
Yang T, Long X, Sangaiah AK, Zheng Z, Tong C (2018) Deep detection network for real-life traffic sign in vehicular networks. Comput Netw 136:95–104. https://doi.org/10.1016/j.comnet.2018.02.026
Kassani PH, Teoh ABJ (2017) A new sparse model for traffic sign classification using soft histogram of oriented gradients. Appl Soft Comput 52:231–246. https://doi.org/10.1016/j.asoc.2016.12.037
Huang Z, Yu Y, Gu J, Liu H (2017) An efficient method for traffic sign recognition based on extreme learning machine. IEEE Trans Cybern 47(4):920–933. https://doi.org/10.1109/TCYB.2016.2533424
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 Photogr Remote Sens 113:106–123. https://doi.org/10.1016/j.isprsjprs.2016.01.005
Jurisic F, Filković I, Kalafatić Z (2015) Multiple-dataset traffic sign classification with OneCNN. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR). IEEE, pp 614–618. https://doi.org/10.1109/ACPR.2015.7486576
Mathias M, Timofte R, Benenson R, Van Gool L (2013) Traffic sign recognition—how far are we from the solution? In: The 2013 international joint conference on neural networks (IJCNN). IEEE, pp 1–8. https://doi.org/10.1109/IJCNN.2013.6707049
Lu K, Ding Z, Ge S (2012) Sparse-representation-based graph embedding for traffic sign recognition. IEEE Trans Intell Transp Syst 13(4):431, 1515–1524. https://doi.org/10.1109/TITS.2012.2220965
Madani A, Yusof R (2017) Traffic sign recognition based on color, shape, and pictogram classification using support vector machines. Neural Comput Appl 30:2807–2817. https://doi.org/10.1007/s00521-017-2887-x
Yang Y, Luo H, Xu H, Wu F (2016) Towards real-time traffic sign detection and classification. IEEE Trans Intell Transp Syst 17(7):2022–2031. https://doi.org/10.1109/TITS.2015.2482461
Yin S, Deng J, Zhang D, Du J (2017) Traffic sign recognition based on deep convolutional neural network. In: CCF Chinese conference on computer vision. Springer, Singapore, pp 685–695. https://doi.org/10.1007/978-981-10-7299-4_57
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345–1359. https://doi.org/10.1109/TKDE.2009.191
Ahn E, Kumar A, Kim J, Li C, Feng D, Fulham M (2006) X-ray image classification using domain transferred convolutional neural networks and local sparse spatial pyramid. In: IEEE 13th ISBI, pp 855–858. https://doi.org/10.1109/ISBI.2016.7493400
Protopapadakis E, Schauer M, Pierri E, Doulamis AD, Stavroulakis GE, Böhrnsen JU, Langer S (2016) A genetically optimized neural classifier applied to numerical pile integrity tests considering concrete piles. Comput Struct 162:68–79. https://doi.org/10.1016/j.compstruc.2015.08.005
Xie L, Yuille A (2017) Genetic CNN. In: ICCV, pp 1388–1397
Young SR, Rose DC, Karnowsky TP, Lim S-H, Patton RM (2015) Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: Proceedings of the workshop on machine learning in high-performance computing environments. https://doi.org/10.1145/2834892.2834896
Loshchilov I, Hutter F (2016) CMA-ES for hyperparameter optimization of deep neural networks. arXiv preprint arXiv:1604.07269
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Zhu Z, Liang D, Zhang S, Huang X, Li B, Hu S (2016) Traffic-sign detection and classification in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2110–2118
Timofte R, Van Gool L (2011) Sparse representation based projections. In: Proceedings of the 22nd British machine vision conference-BMVC 2011. BMVA Press, pp 61-1. http://dx.doi.org/10.5244/C.25.61
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jain, A., Mishra, A., Shukla, A. et al. A Novel Genetically Optimized Convolutional Neural Network for Traffic Sign Recognition: A New Benchmark on Belgium and Chinese Traffic Sign Datasets. Neural Process Lett 50, 3019–3043 (2019). https://doi.org/10.1007/s11063-019-09991-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-019-09991-x