Designing smart access for transp orts to the territory of «Turan» University

Authors

  • A. Bektemessov Turan University
  • V. E. Vlassyuk Turan University

DOI:

https://doi.org/10.26577/JMMCS.2020.v105.i1.16

Keywords:

automated access, computer vision, access control, machine learning

Abstract

With the development of society, the issue of ensuring human security in all its aspects has become increasingly important. This scientific article considers software and technical means for creating automatic recognition of objects, in particular car numbers. Purpose of the work. Development of a system of automatic access of vehicles to the parking area of «Turan» University. This work demonstrates the possibility of using trainee systems at checkpoints, while using a microcomputer RassberryPi 3 Model B, which is characterized by its mobility and modularity. The field of research is computer vision and machine learning used means of mathematical statistics, numerical methods, optimization methods. As a result of the work, a model has been created that demonstrates the operability of the system. The system runs on a mini computer, using a Rassberry camera for number recognition, a servo motor to demonstrate the operation of the access control system. When the camera enters the area of visibility, the reading system is activated, the number is recognized by algorithms and checked by base, and in case of successful check, the barrier is opened. This computer is able to learn further at a real site.

References

1. Петин В.А. Микрокомпьютеры Raspberry Pi. Практическое руководство, БХВ-Петербург, 2015. - Т.2, - С.46-47.
2. Саймон М. Raspberry Pi. Сборник рецептов. Решение программных и аппаратных задач, O'Reilly, 2017. - С.354-368.
3. Cook M., Evans J., Craft B. Raspberry Pi Projects For Dummies, O'Reilly, 2015. - С.264-276.
4. Membrey P., Hows D. Learn Raspberry Pi 2 with Linux and Windows 10, O'Reilly , 2015. - V.3, - P. 125 - 167.
5. Старовойтов А.А. Настройка аппаратных средств в Linux, БХВ-Петербург, 2006. -Т.2, - С. 60-75
6. Hammell B. Arduino Meets Linux. The Users Guide to Arduino Yun Development, 2015. - P. 15 - 23.
7. Hertzog R., Mas R. The Debian Administrator's Handbook, Debian Jessie from Discovery to Mastery, Freexian, 2015. - P. 351 - 364.
8. Williams J.G. Debian GNU/Linux Desktop Survival Guide, Togaware, 2015. - P. 254 - 256.
9. Guido S., Muller A. Introduction to Machine Learning with Python. A Guide for Data Scientists, O'Reilly \& Associates, 2017. - T.1, - P. 59- 64.
10. Маккинни У. Python и анализ данных, ДМК Пресс, 2015. - Т.1 - С. 282-283.
11. Лутц М. Изучаем Python, Символ-Плюс, 2011. -Т.4, - С. 564-568
12. www.jetbrains.com/ru-ru/pycharm, Дата обращения: 15.08.2019
13. https://devpractice.ru/files/books/python/Python.Lessons.pdf, Дата обращения: 16.08.2019
14. Когаловский М.Р. Энциклопедия технологий баз данных, М.:Финансы и статистика, 2012. -Т.2, - С. 120-125
15. Мартишин С., Симонов В., Храпченко М. Базы данных. Практическое примечание СУБД SQL и NoSQL. Учебное пособие, Форум, Инфра-М, 2016. - С. 160-176
16. Guido S., Muller A. Learning OpenCV 3 Computer Vision with Python - Second Edition, O'Reilly Media, 2017. - V.2, - P. 564 - 570.
17. Beyeler M. Machine Learning for OpenCV: Intelligent image processing with Python, Packt Publishing, 2017. - P. 215 - 235.

Downloads

Published

2020-04-06