INFORMATION TECHNOLOGY FOR RECOGNITION OF ROAD SIGNS USING A NEURAL NETWORK
DOI:
https://doi.org/10.30837/2522-9818.2019.8.130Keywords:
image recognition, neural network, computer vision, information technologyAbstract
The subject of the study is the methods and tools for automation of recognition of road signs at the level of software implementation. Detection of road signs is associated with the processing of a significant amount of video data in real time, which requires significant computing power. Therefore, the purpose of the work is to automate the process of recognition of road signs for filling the databases of navigators, which will allow operatively provide drivers with up-to-date information on established road signs. The following tasks are solved: analysis of methods and software for image recognition; development of the search algorithm for characters in the video frame; implementation of the definition of the contour of the sign; realization of a convolutional neural network for recognition of a sign; testing of applied information technology work. Methods are used: convolutional neural networks; Viola-Jones's method for recognizing objects in an image, the Bousting method as a way to accelerate the recognition process with a large amount of information. Results: Different approaches to the identification of symbols on images, various software tools for object recognition, image transformation for optimal fragment are considered. An algorithm for detecting and recognizing the sign is developed. Using the Viola-Jones method, a fast way to calculate the values of attributes using the integral representation of an image is implemented. The recognition process takes place by constructing a convolutional neural network. Features of the layers of the roller network are considered. Schematically illustrated script recognition. The process of interaction of the system with different data sources is represented by a diagram of precedents. The main result is the creation of information technology for the automated recognition of road signs. The algorithm of its work is presented in the form of a sequence diagram. Conclusions. Using the applied application information technology, recognition of road signs is made with an average probability of 88%, which allows automating the process of filling the database of navigators to a large extent, to increase the reliability and productivity of the given process.References
Shneier, M. (2006), "Road sign detection and recognition", Unmanned Systems Technology VIII, International Society for Optics and Photonics, Vol. 6230 (623016). DOI: https://doi.org/10.1117/12.660219
Yakimov, P. Yu. (2013), "Preliminary processing of digital images in the systems of localization and recognition of road signs" ["Predvaritel'naya obrabotka tsifrovykh izobrazheniy v sistemakh lokalizatsii i raspoznavaniya dorozhnykh znakov. Komp'yuternaya optika"], Computer Optics, Vol. 37, No. 3. P. 401–405.
Malyeyeva, О., Nosova, N., Fedorovych, O., Kosenko, V. (2019), "The Semantic Network Creation for an Innovative Project Scope as a Part of Project Knowledge Ontology", CEUR Workshop Proceedings. Proceedings of the 3rd International Conference on Computational Linguistics and Intelligent Systems (COLINS-2019), Vol. I, P. 301–311.
Bolohova, N. Ruban, I. (2019), "Image processing models and methods research and ways of improving marker recognition technologies in added reality systems", Innovative Technologies and Scientific Solutions for Industries, No. 1 (7), P. 25–33. DOI: https://doi.org/10.30837/2522-9818.2019.7.025
Lisitsyn, S. O., Baida, O. A. (2012), "Recognition of road signs using the method of support vectors and histograms of oriented gradients" ["Raspoznavaniye dorozhnykh znakov s pomoshch'yu metoda opornykh vektorov i gistogramm oriyentirovannykh gradiyentov"], Computer optics, Vol. 36, No. 2, P. 289–295.
Zhu, Y., Zhang, C., Zhou, D., Wang, X., Bai, X., Liu, W. (2016), "Traffic sign detection and recognition using fully convolutional network guided proposals", Neurocomputing, Vol. 214, P. 758–766. DOI: http://dx.doi.org/10.1016/j.neucom.2016.07.009
Bodyanskiy, Y., Perova, I., Zhernova, P. (2019) "Online fuzzy clustering of high dimension data streams based on neural network ensembles", Innovative Technologies and Scientific Solutions for Industries, No. 1 (7), P. 16–24. DOI: https://doi.org/10.30837/2522-9818.2019.7.016
Chigorin, A. A., Konushin, A. S. (2013), "Experiments with learning methods for recognizing road signs on synthetic data" ["Eksperimenty s obucheniyem metodov raspoznavaniya dorozhnykh znakov na sinteticheskikh dannykh"], Science and education: a scientific publication MSTU. N.E. Bauman, No. 08, P. 315–324. DOI: https://doi.org/10.7463/0813.0603378, available at : https://bmstu.ru/doc/603378.html
Viola, P. A., Jones, M. J. (2004), "Robust realtime face detection", International journal of computer vision, Vol. 57, No. 2, P. 137–154.
LeCun, Y., Bengio, Y. (1994), "Wordlevel training of a handwritten word recognizer based on convolutional neural networks", Proceedings of the International Conference on Pattern Recognition, Jerusalem, Israel, Vol. 2, P. 88–92.
Lawrence, S., Giles, C. L., Tsoi, A. C., Back, A. D. (1997), "Face recognition: a convolutional neural network approach", IEEE Transactions on Neural Networks, Vol. 8, No. 1, P. 98–113.
Open Source Computer Vision, available at : https://docs.opencv.org/3.4/index.html
Kaehler, A., Bradski, G. (2016), Learning OpenCV 3: computer vision in C++ with the OpenCV library, Reilly Media, Inc., 1024 р.
Dergachev, K. Yu., Krasnov, L. A., Pyavka, I. A. (2018), "Analysis of the performance of technical vision algorithms in trajectory measurement problems" ["Analiz raboty algoritmov tekhnicheskogo zreniya v zadachakh trayektornykh izmereniy"], Electrotechnic and Computer Systems, No. 27 (103), P. 187–195. DOI: https://doi.org/10.15276/eltecs.27.103.2018.21
Yaloveha, V., Hlavcheva, D., Podorozhniak, A. (2019), "Usage of convolutional neural network for multispectral image processing applied to the problem of detecting fire hazardous forest areas", Advanced Information Systems, Vol. 3, No. 1, P. 116–120. DOI: https://doi.org/10.20998/2522-9052.2019.1.19
Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012), ЄImagenet classification with deep convolutional neural networks", Advances in neural information processing systems, No. 25, P. 1097–1105.
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T. (2014), "Caffe: Convolutional architecture for fast feature embedding", Proceedings of the 22nd ACM international conference on Multimedia, ACM, P. 675–678.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2019 Elena Yashina, Roman Artiukh, Nikolai Рan, Andrei Zelensky
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
