main| new issue| archive| editorial board| for the authors| publishing house|
Πσρρκθι
Main page
New issue
Archive of articles
Editorial board
For the authors
Publishing house

 

 


ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 9. Vol. 29. 2023

DOI: 10.17587/it.29.484-491

R. M. Khusainov, Postgraduate Student, N. G. Talipov, PhD (Technical Science), Associate Professor, A. S. Katasev, Dr. Sci. (Technical Science), Professor,
Kazan National Research Technical University named after A. N. Tupolev

Intelligent System for Recognition of Road Infrastructure Objects Using a Neural Network Model

The article deals with the problem of recognition of road infrastructure objects. The expediency of solving this problem using an intelligent system based on a neural network model is updated. In order to develop it to solve the problem, the collection of initial data, the choice of libraries, the construction of the architecture and the training of the neural network were carried out. The initial data for constructing the model was obtained when generating queries in a search engine and presented in the form of images of traffic signs, road markings and traffic lights. To build a neural network, training and test samples were formed for 3 classes of images, taking into account various road conditions. When building a neural network model, the activation functions Relu and Softmax were used. The neural network model includes 4 convolution layers, 2 subsampling layers and 2 fully connected layers. The IDLE development environment was used to train the model. The program code is written in the Python 3.9.7 programming language. The neural network model was trained for 10 epochs. An example of the operation of the system and the results of testing the developed built model are presented. Studies have shown that the developed intelligent system and neural network model for recognizing road infrastructure objects are adequate, and its accuracy is 92 %. The achieved accuracy of the neural network model is not inferior to the accuracy of other methods for classifying objects in images.
Keywords: object recognition, intelligent system, road infrastructure objects, computer vision algorithms, driver, neural network model, network architecture, neural network, classification method, recognition accuracy

P. 484-491

References

  1. Klyuchikov A. V., Bol'shakov A. A., Grepechuk Yu. N., Lobanov V. V. Device for recognition of obstacles for visually impaired and blind people, Fundamental'nyye issledovaniya, 2017, no. 10-1, pp. 13—18 (in Russian).
  2. Factors affecting the likelihood of an accident, availableat: http://road-traffic-safety.blogspot.com/2011/01/dtp-factory.html (accessed 03/17/2023).
  3. Kapustina E. G. The main risk factors in road traffic and their prevention, Nauchnyy vestnik Orlovskogo yuridicheskogo instituta MVD Rossii imeni V. V. Luk'yanova, 2021, no. 3 (88), pp. 119—126 (in Russian).
  4. Factors affecting road safety, available at: https://www.driver-helper.ru/bezopasnost-dorozhnogo-dvizheniya/faktory-vliyayushhie-na-bezopasnost-dorozhnogo-dvizheniya (date of access: 03/17/2023).
  5. Khusainov R. M., Talipov N. G., Katasev A. S. Neural network convolutional model of traffic sign recognition in intelligent transport systems, Vestnik NTSBZHD, 2022, no. 4 (54), pp. 157—163 (in Russian).
  6. Indicators of the state of road safety, available at: http:// stat.gibdd.ru/ (date of access: 03/17/2023).
  7. Filatov D. M., Ignatiev K. V., Serykh E. V. Neural Network System for Recognizing Road Signs, Mezhdunarodnaya konferentsiya po myagkim vychisleniyam i izmereniyam, 2017, vol. 1, pp. 513—515 (in Russian).
  8. Evsina V. A., Shirobokova S. N., Zhzhonov V. A., Evsin V. A. Modeling and implementation of the process of recognizing traffic signs when determining the situation on the road using artificial neural networks, Inzhenernyy vestnik Dona, 2020, no. 4 (88), pp. 144—151 (in Russian).
  9. Pyrnova O. A., Zaripova R. S. Neural Network System for Recognizing Traffic Signs, International Journal of Advanced Studies, 2022, vol. 12, no. 3-2, pp. 46-51 (in Russian).
  10. Elizarov D. A. Development of a system for recognizing road objects, Omskiy nauchnyy vestnik, 2017, no. 4 (154), pp. 120—123 (in Russian).
  11. Voronov S. V. Detection of road signs in real time on mobile devices, Telecommunication devices and systems, 2018, vol. 8, no. 3, pp. 22—26 (in Russian).
  12. Gurin V. I. Detection and recognition of traffic signs using technical vision and machine learning, Nauka bez granits, 2020, no. 5 (45), pp. 75—82 (in Russian).
  13. Zaidulin K. M., Zaidulin S. M., Fakhmi Sh. S. System for detecting road signs in a video stream, Nauka nastoyashchego i budushchego, 2018, vol. 1, pp. 43—47 (in Russian).
  14. Shein V. A., Pak A. O. Road lane line detection with hough transform, Theoretical & Applied Science, 2020, no. 12 (92), pp. 401—408.
  15. Kupriyanov A. L. Mathematical model of a video system for recognizing road markings and traffic signals, Nauka bez granits, 2019, no. 4 (32), pp. 40—45 (in Russian).
  16. Ilkin I. R. The use of computer vision to control the marking of the road lane, Molodezhnaya nauka kak faktor i resurs inno-vatsionnogo razvitiya. Sbornik statey IV Mezhdunarodnoy nauchno-prakticheskoy, 2021, pp. 246—253 (in Russian).
  17. Kirpichnikov A. P., Lyasheva S. A., Shakirzyanova A. A., Shleimovich M. P., Shakirzyanov R. M. Algorithm for detecting light signals of vehicles and traffic lights, Vestnik tekhnologichesk-ogo universiteta, 2019, vol. 22, no. 9, pp. 130—133 (in Russian).
  18. Kirpichnikov A. P., Lyasheva S. A., Shakirzyanova A. A., Shleimovich M. P., Shakirzyanov R. M. Detection of circles in images using the Hough method and fast radial symmetry transfor­mation, Vestnik tekhnologicheskogo universiteta, 2019, vol. 22, no. 8, pp. 164—167 (in Russian).
  19. Shakirzyanov R. M., Shakirzyanova A. A. Detection of object centers in images using the Hough methods and fast radial symmetry transformation, V sbornike: XXIV Tupolevskiye chteniya (shkola molodykh uchenykh). Materialy Mezhdunarodnoy molodezhnoy nauchnoy konferentsii, 2019, pp. 497—500 (in Russian).
  20. Shakirzyanov R. M. Detection of traffic signals using color segmentation and a radial symmetry detector, Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta, 2020, vol. 16, no. 6, pp. 25—33 (in Russian).
  21. Sabirov A. I., Katasev A. S., Dagaeva M. V. Neural network model of traffic sign recognition in intelligent transport systems, Komp'yuternoye issledovaniye i modelirovaniye, 2021, vol. 13, no. 2, pp. 429—435 (in Russian).
  22. Khorkov A. A., Tsarikov A. A. Problematic issues of legal regulation in the implementation of federal state supervision in the field of road safety, Dal'niy vostok: problemy razvitiya arkhitekturno-stroitel'nogo kompleksa, 2021, no. 1, pp. 200—204 (in Russian).
  23. Yudakov D. S., Korotchenkov A. I. Libraries Open CV as a basis for vision systems, Okhrana, bezopasnost', svyaz', 2016, no. 1-1, pp. 219—222 (in Russian).
  24. Barysheva N. N., Baryshev D. D., Dorokhov R. E. Processing and visualization of data on the electrical properties of wheat grains using the Matplotlib library, Nauka i obrazovanie, 2020, vol. 3. no. 2, pp. 375—380 (in Russian).
  25. Pylov P. A. Using and representing arrays in the Numpy library, Innovatsii. Nauka. Obrazovaniye, 2020, no. 23, pp. 258—266 (in Russian).
  26. Padhi A., Sahoo G., Maity S. Intelligent intrusion detection using Tensorflow, Smart Innovation, Systems and Technologies, 2021, vol. 153, pp. 653—662.
  27. Vasyaeva T. A., Martynenko T. V., Subbota N. S. Forecasting financial time series using neural networks using the Keras library in Python, Informatika i kibernetika, 2019, no. 2 (16), pp. 41—50 (in Russian).
  28. Katasev A. S. A neuro-fuzzy model for the formation of fuzzy rules for assessing the state of objects under uncertainty, Komp'yuternyye issledovaniya i modelirovaniye, 2019, vol. 11, no. 3, pp. 477—492 (in Russian).
  29. Homonenko A. D., Yakovlev E. L. Substantiation of the architecture of a convolutional neural network for autonomous recognition of objects in images by an onboard computer system, Naukoyemkiye tekhnologii v kosmicheskikh issledovaniyakh Zemli, 2018, vol. 10, no. 6, pp. 86—93 (in Russian).
  30. Matveev D. A., Petrunicheva A. S. Development of a convolutional neural network model for the classification of Russian road signs, Politekhnicheskiy molodezhnyy zhurnal, 2020, no. 9 (50), pp. 2—9 (in Russian).
  31. Karimov M. T., Nikonov V. V. Performance Comparison of Convolutional Neural Network Models on a GPU, Informatsionnyye i telekommunikatsionnyye tekhnologii, 2021, no. 52, pp. 42—48 (in Russian).
  32. Demenkova T. A., Shpieva E. V. Building models of a convolutional neural network for solving problems of pattern recognition, Nauchno-tekhnicheskiy vestnik Povolzh'ya, 2020, no. 5, pp. 76—79 (in Russian).
  33. Jayadhas S. A., Roslin S. E. Performance analysis of malicious node detection in wireless multimedia sensor networks using modified lenet architecture, International Journal of Computer Networks and Applications, 2022, vol. 9, no 2, pp. 179—188.
  34. Kolesov A. M., Pak L. T., Talipov N. G. Vehicle license plate recognition system, Vestnik tekhnologicheskogo universiteta, 2022, vol. 25, no. 4, pp. 115—119 (in Russian).
  35. Khusainov R. M., Talipov N. G., Katasev A. S. A model of traffic sign recognition using a convolutional neural network, Vestnik tekhnologicheskogo universiteta, 2022, vol. 25, no. 12, pp. 154—157 (in Russian).
  36. Khusainov R. M., Talipov N. G. Intelligent traffic sign recognition system based on a convolutional neural network, Computer program registration certificate 2022616988.
  37. Paklin N. B., Oreshkov V. I. Business analytics: from data to knowledge, St. Petersburg, Piter, 2013, pp. 704.

 

To the contents