Асистент паркування як модуль системи розумного міста

АСИСТЕНТ ПАРКУВАННЯ ЯК МОДУЛЬ СИСТЕМИ РОЗУМНОГО МІСТА

MULTISOURCE INTELLIGENT PARKING ASSISTANT

 Сторінки: 56-60. Номер: №5, 2022 (313)  
DOI: https://www.doi.org/10.31891/2307-5732-2022-313-5-56-60
Автори: НОВОСАД Марія-Руслана
Національний університет “Львівська політехніка”
ORCID ID: 0000-0003-3005-6614
e-mail: ruslana.novosad.3@gmail.com
NOVOSAD Mariia-Ruslana
Lviv Polytechnic National University

Анотація мовою оригіналу

В роботі наведено результати розробки застосунку для швидкого і зручного пошуку місця для паркування. Система є модулем розумного міста та орієнтована на житлові комплекси, опрацьовує дані з різних джерел та відображає статуси паркомісць територій для паркування, здійснює пошук відповідного паркомісця за номером транспортного засобу. Створювана система складається з трьох основних компонент: зберігання та обробка запитів, коректне відображення даних, обробка зображення.
Ключові слова: розумне місто, паркування, автомобіль, згорткова нейронна мережа, застосунок.

Розширена анотація англійською  мовою

Problem searching for a parking space is time-consuming and highly relevant both in Ukraine and abroad.  Time spent searching for a parking space leads to excessive traffic, more traffic jams, air pollution and increased fuel consumption. These factors also affect the daily stress levels of drivers. Due to this, the process of finding a parking space should be fast and convenient. At the same time, there has been significant development of real estate in Lviv over the past few years. Accordingly, the need for organizing the process of parking cars of residents of residential areas is growing. This paper presents the results of the development of an application for a quick and convenient search for a parking space. A review of similar software applications was conducted. Proposed solutions use various technologies to solve the problem of searching for a free parking space including IoT, sensors, machine learning for image recognition. Even though they solve the problem of searching for a free parking space, most of them can be expensive to implement, maintain, they don’t provide the ability to work with different data sources. An activity diagram of system is presented and it shows two main flows of the system: displaying the current state of parking spaces and displaying parking space by the number of the car entering the territory of the complex. System consists of three modules. The first module is responsible for working with different data sources, storing the status of parking spaces, processing requests. Image processing module is responsible for determining the occupied and free parking spaces from the image. The third module is responsible for the correct display of parking spaces and their statuses. It is also demonstrated how the application works with different data sources and how exceptions are handled. The system works correctly and has a сlear interface. The parking assistant is a great helper and significantly reduces the time required to find a free parking space.
Keywords: smart city, parking, car, convolutional neural network, application.

Література

1. Sperling D., Gordon D. Two billion cars transforming a culture. P. 9.
2. Брикайло Ю. В 2019 році введено в експлуатацію 775 багатоквартирних будинків площею більше 11 000 000 кв. м / Юрій Брикайло. –
3. Graham Cookson, Bob Pishue The impact of parking pain in the us, uk and germany. inrix research. P. 44.
4. ParkSetup – parking guidance systems manufacturer. URL: http://www.parksetup.com/en_us/
5. Home – Cleverciti | smart parking for smart cities. URL: https://www.cleverciti.com
6. SoftServe is testing a smart parking system. URL: https://itcluster.lviv.ua/softserve-teste-rozumnu-systemu-parkingu/
7. Bhandare A., Bhide M. V., Gokhale P., Chandavarkar R. Applications of convolutional neural networks. Vol. 7. P. 10.
8. Amato G., Carrara F., Falchi F. [et al.] Deep learning for decentralized parking lot occupancy detection. Expert Systems with Applications. 2017. Vol. 72. P. 327–334.
9. Kingma D. P., Ba J. Adam: a method for stochastic optimization. arXiv:1412.6980 [cs]. 2017.

References

1. Sperling D., Gordon D. Two billion cars transforming a culture. 2008. P. 9.
2. Brykailo Yu. V 2019 rotsi vvedeno v ekspluatatsiiu 775 bahatokvartyrnykh budynkiv ploshcheiu bilshe 11 000 000 kv. m / Yurii Brykailo. – 2020.
3. Graham Cookson, Bob Pishue The impact of parking pain in the us, uk and germany. inrix research. 2017. P. 44.
4. ParkSetup – parking guidance systems manufacturer. URL: http://www.parksetup.com/en_us/
5. Home – Cleverciti | smart parking for smart cities. URL: https://www.cleverciti.com
6. SoftServe is testing a smart parking system. URL: https://itcluster.lviv.ua/softserve-teste-rozumnu-systemu-parkingu/
7. Bhandare A., Bhide M. V., Gokhale P., Chandavarkar R. Applications of convolutional neural networks. 2016. Vol. 7. P. 10.
8. Amato G., Carrara F., Falchi F. [et al.] Deep learning for decentralized parking lot occupancy detection. Expert Systems with Applications. 2017. Vol. 72. P. 327–334.
9. Kingma D. P., Ba J. Adam: a method for stochastic optimization. arXiv:1412.6980 [cs]. 2017.