Unauthorized Parking Notification System

Abstract

This paper focuses on development of an parking notification system on Raspberry Pi. In parking system, Automatic License Plate Recognition (ALPR) is becoming an increasingly practical security solution, while security and possession are the most discussed issues nowadays. However, similar systems on the market currently only focus on security, which only provides authorization at carpark entrance to prevent unauthorized personnel from entering the compound. There may be an infringement of ownership happens, where a parking lot owned by a person occupied by irresponsible car owner. Besides, although there are subscription-based services available for ALPR, but most of them are expensive due to their deeply customized high accuracy, and may be unaffordable to everyone. Most carpark systems also lack of the ability to send notification to lot owner with unauthorized vehicle information. Therefore, this study is aimed to design a system that able to check authorization at both entrance site and parking lot site, to implement an open-source solution to the system, and to equip notification ability to the system. In this study, license plate detection/localization was implemented to get the Region of Interest (ROI) from input images. License plate character recognition was then executed to perform authorization checking with database. After the authorization checking is completed, the result with relevant information will be sent as notification to parking lot owners. The performance of plate detection algorithms will be evaluated based on their accuracy. The plate detection algorithm with Haar Cascade Classifier had produced a high segmentation accuracy, which is 96.875%. Meanwhile, for the overall system accuracy (also known as OCR/plate recognition accuracy) had achieved 71.875% for Malaysian License Plate. In conclusion, a system with ALPR and notification abilities that emphasis on both security and possession is successfully developed.