Smart Parking System

Dhruv Khanna(RA1511003010624)
Department of Computer Science Engineering
SRM Institute of Science
Technology SRM University
Chennai, India
[email protected]

Abstract— The objective of our project is to find a better and less time-consuming method for payments in parking lots and also, providing information regarding vacant spaces available in parking lots. With IoT technology and mobile applications, in this, we propose a design and development of a real smart parking system that allows user to pay the parking fees easily through the app itself and also help user to locate the space where the vehicle can be parked in order to reduce traffic in the parking area.

Keywords: IoT, smart parking.

In many large cities and busy business areas, vacant parking space is very difficult to find. As the number of vehicles is increased, it is more difficult and takes more time to find available parking slots. The traffic jam problem is not only occurring on the roads but also in the parking areas where the parking space is limited. The smart city plan of many countries including Thailand requires smart parking services that can help users to locate available parking area in order to reduce time and traffic problems. However, most of the provided parking systems is considered to be just “informative parking system (IPS)” rather than “smart parking system (SPS)” because it only provides information about location of parking areas and the number of vacant spaces in that parking area but it cannot locate the exact location of the vacant parking slot.

Related work
In previous works, there are several solutions have been proposed in 2, 3 and 4 for improving parking process. Paper 2 presented a smart parking system using ultrasonic sensors.

In 3 a vehicle license plate detection method using neural network approaches are proposed.

4 In this paper, we reviewed a sensor-based smart parking solution, described how it was deployed and its vehicle detection algorithm.

This system helps management and improvement a parking area. these are easy for user to decision parked vehicle. The user can get information about the parking location, number of parking slots and all other possible a parking area’s information. Those provides user convenient into application and also has a feature of functions such as billing, which helps users to pay online on application mode. The system uses computer vision to extract vehicle registration plate at parking slot. The result is consisted to database of user application, which user can receive notification massages on smartphone, which to enchain security in parking area this be confidence to user.

Before designed system assumes that 6LR, equipped with a light sensor, are placed on each parking lot in order to detect cars’ presence, while 6LRR nodes are placed on poles located near the parking spaces reserved for people with special authorizations. Indeed, in the propose system, the 6LRR nodes are used to check that only authorized cars, labelled with special RFID tags, occupy the reserved parking places. In the future, car plates equipped with special RFID tags could be used to store a number of information about the car and its owner, as well as optional special permission for impaired people or for granting access in traffic restricted areas. The retrieved information is delivered to the IoT Smart Gateway, which is connected, on the one hand, directly with the HSN and, on the other hand, with the Internet through a 3G-communication interface. The gateway plays the role of 6LBR, enabling the communication between HSN nodes and remote users. The gateway, in turn, allows the RESTful communication with the cloud platform.This last one is equipped with the following different modules: (i) Data Storage Module, in charge of storing the sensed data; (ii) Device Management Module, responsible to control and manage sensors; (iii) Virtual Card Management Module, designed to manage the payments; and (iv) a Management Application (MA), able to execute the business logic. When the MA realizes that a reserved parking spot has been occupied, it checks if a new tag has been read by 6LRR node responsible for controlling that specific reserved space, and, in such a case, it verifies the car’s authorizations. In case of improper use of a reserved space or expiration of parking receipt, the MA exploits Push Notifications (PN) to inform the nearest traffic cops. The REST paradigm has also been adopted to make the collected data easily accessible from the users. To this purpose, two different mobile applications have been developed, called TrafficApp and DriverApp. More in detail, in the designed system the traffic cops are equipped with a smartphone connected to a portable RFID reader and running the TrafficApp. Through this App, traffic cops can interact directly with the tags placed on the cars and check their permissions or retrieve information stored into the Cloud. The TrafficCop App allows operators to issue a fine and to update the memory content of RFID tags with important information to remind (e.g. the date and time of the last check, information about the expiration of the authorization, etc.). The DriverApp allows the driver to find the parking spaces available in a given area, get the right directions to the selected parking spot, pay the parking fee, check the remaining parking time and receive notifications when the purchased time is expiring.

System Overview
Mobile Application will send request informative parking spaces to cloud, it responds the requests into manner map of parking area.

The available/unavailable parking spaces are displayed simply such as parking slots graphic, colors and symbols on mobile application.

Real-time (available/unavailable) informative parking spaces is updated immediately on mobile application.

When drivers parked into parking slot. the notification to fill license plate number of driver is indicated on application.

The parking slot is display information license plate of vehicle that his/her already confirmed, status unavailable and location of parking slot such as number of slot and floor of parking slot.

Drivers may receive other service of mobile application such as tracking car position and timer.

Application is send notification messages timer car payment to remind driver before drivers exited their car parked location, they can pay parking fee via online payment on mobile application.

The informative parking slot on mobile application is reminded drivers to find parked location.

Drivers can track vehicle position, they can easily find their car and see current parking fee via mobile application.

Required Technologies
License plate extract text: it need to be more accuracy, Optical Character Recognition (OCR) that extract “text” from image, and it can be detected in an open environment.

Ultrasonic Sensor: these need to be more stable and less errors although it launches for the long period as mention in related work.

Embedded controller: controller hardware devices and connection to Cloud service.

Camera: the quality of pixel be clear and faster capture.

Ultrasonic sensor — (HC-SR04): This is used at each parking slots location to detect the vehicles within the range. The Raspberry Pi will forward detection to cloud, which is updated status available/unavailable.

C. Smart Gateway
The Smart Gateway represents an important element of the designed architecture. It works as a bridge between the HSN and the cloud platform. It has been realized by connecting a Rasperry Pi 2 Model B board 28, equipped with the Raspian operating system, to the 6LowPAN Border Router. The gateway has been also equipped with a GPRS module, a GPS module, and the SCM SCL3711 13.56 MHz NFC contactless reader 29. Raspberry Pi is a credit card-sized computer powered by the Broadcom BCM2836 system-on -a-chip (SoC). This SoC includes a quad-core ARM Cortex-A7 CPU, clocked at 900 MHz. It is equipped with 1 GB of RAM and powered by a 5 V micro USB AC charger. From a functional point of view, it is mainly composed of two different blocks: a proxy and the billing subsystem.

C. Cloud Services
Storing, organizing, and retrieving information related to the occupancy state of parking spaces and environmental conditions are expensive processes from both the computational and memory point of view. For this reason, the cloud seems to represent the solution that best suits this kind of needs, as its storing and computing capabilities allow to process data more efficiently. In the proposed SPS, a cloud platform has been used to store and manage the information retrieved by the HSN and all the data related to payments and expiration of parking fees. We deployed the proposed solution on Amazon Elastic Compute Cloud (EC2). Specifically, as previously introduced, the cloud platform has been equipped with the following modules: (i) Data Storage Module, (ii) Device Management Module, (iii) Virtual Card Management, and (iv) Management Application (MA). In particular, the last one represents the functional core of the proposed SPS, since it is responsible for monitoring the parking lots state and alerting traffic cops in case of critical situations. More in detail, the MA registers itself as an observer to the RFID reader related resources exposed by 6LRR nodes scattered in the parking space, and to the light resources exposed by the 6LR devices used to monitor the parking lots’ state.

Hardware and Cloud Vision API Operation
We propose an algorithm that described the operation of ultrasonic sensor detection vehicle enter into parking slot as which is working to emit frequency sound pulse and calculation distances. Initialize status are defined (1 = available/ 0 = unavailable) at parking slot. First, if it is available, the condition sensor is checked by calculation maximum distance detection this a car parked, so the camera to take a picture then status is updated to unavailable. Second, status is checked again, if it still unavailable because car still exist in parking slot, then the condition sensor is checked by calculation minimum distance if the car exit, so the status will become available again this to prepare for next car. we used cloud vision API technic to analyze vehicle images. This was similar technic OCR engine recognition process and classification method, which is helped our system solve about training dataset, provided accuracy of vehicle registration plate Thai language and to get quickly result training. We created JSON key on cloud API then to put in our Raspberry Pi, and image is uploaded on cloud. these provide result both text characters and numbers.Application operation
When a user wants to use the application, user has register on application, which it need user name, user ID, password and use’s vehicle registration plate. when user has login into the application, these provide functions as we mention in function requirement and system application architecture. that user can select particular parking area, and they can check whose status parking slot is available/unavailable this will decide on themselves to park. When user parked the application has to send notification massage on smartphone, these correspond with vehicle registration plate of use’s database and extraction text. timer function is started counting user parked at the parking slot. when user exited the parking slot, they received notification again this is total timer duration.

This paper proposed an IoT based smart parking system that can provide more than just information about vacant space but also help driver to locate an available parking slot in order to reduce traffic problem in the parking area. The system will detect the vehicle plate number and use it to inform the driver where his/her car is parked and also for the purpose of security monitoring. We design this smart parking system using hardware and software based on IoT concept, and mobile application, the driver can easily check parking information and use mobile payment to pay the parking fee. The goal of our study is to improve the parking process by reducing the time that is required to park a car.

To the best of our knowledge, we are the first to design this kind of device architecture to detect the vehicle/registration plate objects and mobile application. We tested system to find the best range sensor detection for camera to take good view’s picture. The results show that our difference ranges are effect to each part of extraction text, which makes our application to proposed algorithm for provide correctly function services to user.

REFERENCESO. Dokur, S. Katkoori and N. Elmehraz, “Embedded system design of a real-time parking guidance system”, Annual IEEE Systems Conference (SysCon), Orlando, FL, 2016, pp. 1-8.

A. Kianpisheh, N. Mustaffa, P. Limtrairut, and P. Keikhosrokiani, “Smart Parking System (SPS) Architecture Using Ultrasonic Detector”, 2012.

Y. Liu, D. Wei, N. Zhang, M. Zhao “Vehicle-license-plate recognition base on neural network,” IEEE Intermational Conference on Information and Automation, pp. 363 – 336, 2011.

Anderson Ar. Rubem Ka, Gustavo Gi, Itamir Filho, Kayo Goncalves., “Reliability Analysis of an IoT-Based Smart Parking Application for Smart Cities”, IEEE International Conference on Big Data (BIGDATA), 2017.

D. Di Mauro, M. Moltisanti, G. Patane`, S. Battiato, G. M. Farinella, “Park Smart”, IEEE/AVSS International Workshop on Traffic and Street Surveillance for Safety and Security, 2017.

Junhuai Li, Yang An, Rong Fei, Huaijun Wang, “Smartphone Based Car-Searching System for Large Parking Lot”, IEEE 11th Conference on Industrial Electronics and Applications (ICIEA), 2016.

Ray Smith. “An Overview of the Tesseract OCR Engine”, IEEE 9th International Conference on Document Analysis and Recognition, 2007.