Abstract
This research presents an application of the Deep Learning technology in the development of an automatic system detection of traffic signs of Ecuador. The development of this work has been divided into two parts, i) in first a database was built with regulatory and preventive traffic signs, taken in urban environments from several cities in Ecuador. The dataset consists of 52 classes, collected in the various lighting environments (dawn, day, sunset and cloudy) from 6 am to 7 pm, in various localities of Ecuador, ii) then, an object detector based on Faster-RCNN with ZF-Net was implemented as a detection/recognition module. The entire experimental part was developed on the ViiA technology platform, which consists of a vehicle for the implementation of driving assistance systems using Computer Vision and Artificial Intelligence, in real road driving conditions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agencia Nacional de Tránsito del Ecuador. Siniestros Junio 2017 (2018)
Agencia Nacional de Tránsito del Ecuador. Estadísticas de siniestros de tránsito (2021)
Arcos-García, A., Alvarez-García, J., Soria-Morillo, L.: Evaluation of deep neural networks for traffic sign detection systems. Neurocomputing 316, 332–344 (2018)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 34, 743–761 (2012)
Everingham, M., Van-Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. 2, 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4
Fawzi, A., Samulowitz, H., Turaga, D., Frossard, P.: Adaptive data augmentation for image classification. In 2016 IEEE International Conference on Image Processing (ICIP) (2016)
Flores-Calero, M., et al.: Ecuadorian traffic sign detection through color information and a convolutional neural network. IEEE ANDESCON, pp. 1–6 (2020)
Hagl, M., Kouabenan, D.R.: Safe on the road - Does advanced driver assistance systems use affect road risk perception? Transp. Res. Part F: Traffic Psychol. Behav. 73, 488–498 (2020)
He, H., Hui, L., Gu, W.: Transferring digit classifier’s features to a traffic sign detector. In: International Conference on Progress in Informatics and Computing (PIC) (2017)
Hu, Y., Zhang, C., Zhou, D., Wang, X., Bai, X., Liu, W.: Traffic sign detection and recognition using fully convolutional network guided proposals. Neurocomputing 214, 758–766 (2016)
Huang, L.L: Chinese Traffic Sign Database TSDD
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. Int. J. Comput. Vis. 675–678 (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR, abs/1412.6980 (2015)
Lau, M.M., Lim, K.H., Gopalai, A.A.: Malaysia traffic sign recognition with convolutional neural network. Int. J. Comput. Vis., 1006–1010 (2015)
Mogelmose, A., Liu, D., Trivedi, M.M.: Detection of U.S. Traffic Signs. IEEE Trans. Intell. Transp. Syst. 16(6), 3116–3125 (2015)
Mohd-Isa, W.-N., Abdullah, M.-S., Sarzil, M., Abdullah, J., Ali, A., Hashim, N.: Detection of Malaysian traffic signs via modified YOLOv3 algorithm. Int. J. Comput. Vis. (2020)
Nguyen, B.T., Shim, J., Kim, J.K.: Fast traffic sign detection under challenging conditions. Int. J. Comput. Vis. 1, 749–752 (2014)
NVIDIA. Jetson Nano (2021)
World Health Rankings. Road traffic accidents (2017)
Shaoqing, R., Kaiming, H., Ross, G., Sun, J.: Towards real-time object detection with region proposal networks, Faster R-CNN (2015)
Salti, S., Petrelli, A., Tombari, F., Fioraio, N., DiStefano, L.: Traffic sign detection via interest region extraction. Pattern Recogn. 48, 1039–1049 (2015)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(60), 303–338 (2019)
Sirbu, M.-A., Baiasu, A., Bogdan, R., Bogdan, R., Vida, M.: Smart traffic sign detection on autonomous car (2018)
Song, S., Que, Z., Hou, J., Sen, D., Song, Y.: An efficient convolutional neural network for small traffic sign detection. J. Syst. Archit. 97, 269–277 (2019)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The german traffic sign recognition benchmark: a multi-class classification competition. In: IEEE International Joint Conference on Neural Networks, pp. 1453–1460 (2011)
Tabernik, D., Skocaj, D.: Deep learning for large-scale traffic-sign detection and recognition. IEEE Trans. Intell. Transp. Syst. 21(4), 1427–1440 (2020)
World Health Organization WHO. Control de la velocidad (2017)
World Health Organization WHO. Accidentes de tránsito (2018)
XM and MTR. Berkeley AI Research (BAIR)/The Berkeley Vision, Learning Center (BVLC), and community contributors. Caffe library (2016)
Yang, T., Long, X., Sangaiah, A.K., Zheng, Z., Tong, C.: Deep detection network for real-life traffic sign in vehicular networks. Computer Networks (2018)
Yang, W., Zhang, W.: Real-time traffic signs detection based on YOLO network model. International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) (2020)
You, S., Bi, Q., Ji, Y., Liu, S., Feng, Y., Fei, W.: Traffic sign detection method based on improved SSD. Artif. Intell. Decision Support Syst. 11(10), 475 (2020)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks CoRR, abs/1311.2901 (2013)
Zuo, Z., Yu, K., Zhou, Q., Wang, X., Li, T.: Traffic signs detection based on faster R-CNN. In: IEEE 37th International Conference on Distributed Computing Systems Workshops (2017)
Acknowledgment
This work was supported by I &H Tech, through the direct funding, the electronic equipment, the database and the vehicle for the development of the experiments. Also, we thank the reviewers and editor for their helpful comments.
Author information
Authors and Affiliations
Contributions
All the authors have contributed to the development of the work, each one from their expertise.
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Conflict of Interest
The authors declare that there is no conflict of interest.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zabala-Blanco, D., Aldás, M., Román, W., Gallegos, J., Flores-Calero, M. (2022). Automatic Recognition System for Traffic Signs in Ecuador Based on Faster R-CNN with ZFNet. In: Guarda, T., Portela, F., Augusto, M.F. (eds) Advanced Research in Technologies, Information, Innovation and Sustainability. ARTIIS 2022. Communications in Computer and Information Science, vol 1675. Springer, Cham. https://doi.org/10.1007/978-3-031-20319-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-20319-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20318-3
Online ISBN: 978-3-031-20319-0
eBook Packages: Computer ScienceComputer Science (R0)