Development and Optimization of an Intelligent Parking Slot Allotter and Billing System Based on Machine Learning and OCR

Abstract

As a key part of automated vehicle technology intelligent parking slot allotter has become a popular research topic. Intelligent parking slot allotter can grant permission to access the parking area with less human inference. This system can capture image of the vehicle, identify the type of vehicle and allot best fit and optimal parking slot based on its size. It extracts the vehicle’s license plate number, entry time, exit time and calculate total time of the vehicle present with in the parking space. Here, sensors are utilized to identify the presence of the vehicle during entry and exit. Two cameras are utilized to extract features. One camera is used to identify the region of interest, vehicle license plate and identify the characters from the license plate. Tesseract engine and optical character recognition (OCR) functions are used to detect characters from the image. Another camera is utilized to extract features like dimensions of the vehicle using machine learning operations such as convolutional neural network (CNN). Based on the size of the vehicle, best fit parking slot is allotted which gives optimal usage of parking area. These days the quantity of vehicles is expanding exceptionally, so that, searching for an empty parking slot turns out to be increasingly troublesome. By installing the intelligent parking slot allotter, in places like, shopping malls, train stations, and airports the need for searching of parking slot significantly reduces. A past study has demonstrated that traffic because of vehicle’s parking slot searching in downtowns of significant urban communities can represent half of the absolute traffic. With such a hefty traffic jam and time delay in parking slot identifying, intelligent parking slot allotter will be in great demand.