Abstract
Convolutional neural networks (CNN) is widely used for traffic sign recognition. Meanwhile, the compressive sensing technology is developing and applied to the field of image reconstruction in the compressive sensing domain. Therefore, we first propose a traffic sign recognition algorithm based on compressive sensing domain and convolution neural networks for traffic sign recognition. The algorithm converts the image into a compressed sensing domain through the measurement matrix without reconstruction, and can extract the discriminant nonlinear features directly from the compressed sensing domain. In order to improve the accuracy of traffic sign recognition, we further propose a cross-connected convolution neural networks (CCNN). Cross-connected convolution neural networks is a 9 layers framework with an input layer, six hidden layers (i.e., three convolution layers alternating with three pooling layers), a fully-connected layer and an output layer, where the second pooling layer is allowed to connect directly to the fully-connected layer across two layers. Experimental results on well-known dataset show that the algorithm improves the accuracy of traffic sign recognition. The recognition of our algorithm is even possible at low compressive sensing measurement rates.
Similar content being viewed by others
References
Chhabra R, Verma S, Rama Krishna C (2017) A survey on driver behavior detection techniques for intelligent transportation systems. 7th international conference on cloud computing, data science & engineering-confluence, 2017
Jiang D, Huo L, Lv Z, Song H, Qin W (2018) A joint multi-criteria utility-based network selection app-roach for vehicle-to-infrastructure networking. IEEE Trans Intell Transp Syst pp(99):1–15
Jiang D, Xu Z, Wang W, Wang Y, Han Y (2015) A collaborative multi-hop routing algorithm for maximum achievable rate. J Netw Comput Appl 57(2015):182–191
Jiang D, Wang Y, Yao C, Han Y (2015) An effecti-ve dynamic spectrum access algorithm for multi-hop cognitive wireless networks. Comput Netw 84(19):1–16
Jiang D, Huo L, Lv Z et al (2018) A joint multi-criteria utility-based network selection approach for vehicle-to-infrastructure networking. IEEE Trans Intell Transp Syst 19(10):3305–3319
Jiang D, Wang Y, Lv Z et al (2019) Big data analysis-based network behavior insight of cellular networks for industry 4.0 applications. IEEE Trans Ind Inf. Online available: https://doi.org/10.1109/TII.2019.2930226
Xing Y, Lv C, Chen L, Wang H, Wang H, Cao D et al (2018) Advances in vision-based lane detection: algorithms, integration, assessment, and perspectives on ACP-based parallel vision. IEEE/CAA J Automat Sin 5(3):645–661
Jiang D, Xu Z, Li W, Chen Z (2015) Network codi-ng based energy-efficient multicast routing algorithm for multi-hop wireless networks. J Syst Softw 104(2015):152–165
Jiang D, Li W, Lv H (2017) An energy-efficient cooperative multicast routing in multi-hop wireless net-works for smart medical applications. Neurocomputin-g 220(2017):160–169
Jiang D, Wang Y, Han Y et al (2017) Maximum connectivity-based channel allocation algorithm in cognitive wireless networks for medical applications. Neurocomputing 220(2017):41–51
Jiang D, Xu Z, Li W et al (2016) An energy-efficient multicast algorithm with maximum network throughput in multi-hop wireless networks. J Commun Netw 18(5):713–724
Jiang D, Zhang P, Lv Z et al (2016) Energy-efficient multi-constraint routing algorithm with load balancing for smart city applications. IEEE Internet Things J 3(6):1437–1447
Wang F, Jiang D, Wen H et al (2019) Adaboost-based security level classification of mobile intelligent terminals. J Supercomput:1–19. Online available: https://doi.org/10.1007/s11227-019-02954-y
Hmida R, Abdelali AB, Mtibaa A (2018) Hard-ware implementation and validation of a traffic road sign detection and identification system. J Real-Time Image Proc 15(1):13–30
Huo L, Jiang D, Zhu X et al (2019) An SDN-based fine-grained measurement and modeling approach to vehicular communication network traffic. Int J Commun Syst:1–12. Online available: https://doi.org/10.1002/dac.4092
Wang F, Jiang D, Qi S (2019) An adaptive routing algorithm for integrated information networks. China Commun 7(1):196–207
Huo L, Jiang D (2019) Stackelberg game-based energy-efficient resource allocation for 5G cellular networks. Telecommun Syst 23(4):1–11
Haloi M (2015) A novel pLSA based traffic signs classification system. Available at https://arxiv.org/
Jiang D, Huo L, Song H (2018) Rethinking behaviors and activities of base stations in mobile cellular networks based on big data analysis. IEEE Trans Netw Sci Eng 1(1):1–12
Zhao ZH, Yang SP, Ma ZQ (2010) The study of license character recognition based on the convolution neural network LeNet-5. J Syst Simul 22(3):638–641
Shu Y, Huang Y, Li B (2018) Design of deep learning accelerated algorithm for online recognition of industrial products defects. Neural Comput Applic:1–14
Jiang D, Huo L, Li Y (2018) Fine-granularity inference and estimations to network traffic for SDN. PLoS One 13(5):1–23
Mrinal H (2016) Traffic sign classification using deep inception based convolutional networks. Available at https://arxiv.org/
Yi Y, Hengliang L, Huarong X, Wu F (2016) Towards real-time traffic sign detection and classification. IEEE Trans Intell Transp Syst 17:2022–2031
Zhu J, Song Y, Jiang D et al (2018) A new deep-Q-learning-based transmission scheduling mechanism for the cognitive Internet of Things. IEEE Internet Things J 5(4):2375–2385 uestc
Yuan Y, Xiong Z, Wang Q (2019) VSSA-NET: vertical spatial sequence attention network for traffic sign detection. IEEE Trans Image Process 28(7):3423–3434
Zhong SH, Liu Y, Ren FF, Zhang JH, Ren TW (2013) Video saliency detection via dynamic consistent spatio-temporal attention modelling. In: Proceedings of the 2013 AAAI conference on articial intelligence. AAAI, Bellevue, pp 1063–1069
Jiang D, Nie L, Lv Z et al (2016) Spatio-temporal Kronecker compressive sensing for traffic matrix recovery. IEEE Access 4:3046–3053
Huo L, Jiang D, Lv Z (2018) Soft frequency reuse-based optimization algorithm for energy efficiency of multi-cell networks. Comput Electr Eng 66(2):316–331
Tang W, Zhang K, Jiang D (2018) Physarum-inspired routing protocol for energy harvesting wireless sensor networks. Telecommun Syst 67(4):745–762
Mei-Bin Q, Sheng-Shun T, Yun-Xia W, Hao L, Jian-Guo J (2016) Multi-feature subspace and kernel learning for person reidentication. Acta Automat Sin 42(2):299–308
LeCun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436–444
Cheng G, Li Z, Han J, Yao X, Guo L (2018) Exploring hierarchical convolutional features for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(11):6712–6722
Sun M, Zhou Z, Hu Q et al (2019) SG-FCN: a motion and memory-based deep learning model for video saliency detection. IEEE Trans Cybern 49(8):2900–2911
Ulyanov D, Vedaldi A, Lempitsky V (2018) Deep image prior. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9446–9454
Wang T, Yao YT, Chen Y, Zhang MY, Tao F, Snoussi H (2018) Auto-sorting system toward smart factory based on deep learning for image segm-entation. IEEE Sensors J 18(20):8493–8501
Suhas L, Kuldeep K, Pavan T (2016) Direct inference on compressive measurements using convolutional neural networks. Image Process (ICIP):1913–1917
Sun ZJ, Xue L, Xu YM (2012) Review of deep learning research. Comput Appl Res 29(8):2807–2810
Adcock B, Hansen AC, Poon C, Roman B (2017) Breaking the coherence barrier: a new theory for compressed sensing. In: Forum of mathematics, sigma, vol 5. Cambridge University Press, Cambridge
Mehta BB, Coppo S, McGivney DF, Hamilton JI et al (2018) Magnetic resonance fingerprinting: a technical review. Magn Reson Med 81(1):25–46
Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289–1306
Ma J, Ma Y, Li C (2019) Infrared and visible image fusion methods and applications: a survey. Inf Fusion 45:153–178
Jiang D, Wang W, Shi L et al (2018) A compressive sensing-based approach to end-to-end network traffic reconstruction. IEEE Trans Netw Sci Eng 5(3):1–12
Udell M, Horn C, Zadeh R, Boyd S (2016) Generalized low rank models. Found Trends Mach Learn 9(1):1–118
Sankaranarayanan AC, Turaga PK, Baraniuk RG, Chellappa R (2010) Compressive acquisition of dynamic scenes. In: ECCV. Springer, pp 129–142
Wang X, Li G, Varshney PK (2018) Detection of sparse signals in sensor networks via locally most powerful tests. IEEE Signal Process Lett 25(9):1418–1422
Millikan B, Dutta A, Sun Q, Foroosh H (2017) Fast detection of compressively sensed ir targets using stochastically trained least squares and compressed quadratic correlation filters. IEEE Trans Aerosp Electron Syst 53(5):2449–2461
Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: IEEE, Neural Networks (IJCNN), pp 2809–2813
Stallkamp J, Schlipsing M, Salmen J, Igel C (2011) The German traffic sign recognition benchmark: a multi-class classification competition. In: IEEE, Neural Networks (IJCNN), pp 1453–1458
Zaklouta F, Stanciulescu B, Hamdoun O (2011) Traffic sign classification using kd trees and random forests. In: IEEE, Neural Networks (IJCNN), pp 2151–2155
Huang Z, Yu Y, Gu J, Liu H (2016) An effificient method for traffific sign recognition based on extre-me learning machine. IEEE Trans Cybern 99:1–14
Ellahyani A, Ansari ME, Jaafari IE (2016) Traffific sign detection and recognition based on random forests. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2015.12.041
Gudigar A, Chokkadi S, Raghavendra U, Acharya UR (2017) Local texture patterns for traffific sign recognition using higher order spectra. Pattern Recogn Lett. https://doi.org/10.1016/j.patrec.2017.02.016
Gudigar A, Chokkadi S, Raghavendra U, Acharya UR (2019) An efficient traffic sign recognition based on graph embedding features. Neural Comput & Applic 31(2):395–340
Acknowledges
This work was supported by National Natural Science Foundation of China (No. 61571104), Sichuan Science and Technology Program (No. 2018JY0539), Key projects of the Sichuan Provincial Education Department (No. 18ZA0219), Fundamental Research Funds for the Central Universities (No. ZYGX2017KYQD170), and Innovation Funding (No. 2018510007000134). The authors wish to thank the reviewers for their helpful comments. Dr. Jiping Xiong and Dr. Dingde Jiang are corresponding authors of this paper (emails: xjping@zjnu.cn, jiangdd998@sina.com).
Author information
Authors and Affiliations
Corresponding authors
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
Xiong, J., Ye, L., Jiang, D. et al. Efficient Traffic Sign Recognition Using Cross-Connected Convolution Neural Networks Under Compressive Sensing Domain. Mobile Netw Appl 26, 629–637 (2021). https://doi.org/10.1007/s11036-019-01409-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11036-019-01409-1