Data Logging Model for Metropolitan Vehicle Movement Monitoring and Control System

The automotive industry has experienced a spectacular expansion in the last decade, with an increase in number of cars in metropolitan cities. Maintaining track of automobiles based on their plates number in order to manage vehicular traffic properly in the city has posed difficulty. This research presents an artificial intelligence-based technology technique (YOLO) for tracking vehicle movement based on the vehicle's plate number with data logging model and a centralized database structure for vehicles identification and monitoring, using other techniques such as image processing and IoT mechanism for detection and recognition accuracy. In order to create an Intelligent Plate Number Recognition (IPNR) System, this study employs artificial intelligence, computer vision (image processing), laser scanning technologies, and convolutional neural networks (CNN). This model concepts and computations underpin potential solutions to this issue, guaranteeing a range of approaches to achieving the desired outcome. This work focuses on plate number identification using the contours tracing approach, as well as edge identification and sharpening using optical character recognition algorithm based on OpenCV libraries. The vehicle is monitored on real time using the GPS technology where the vehicle plate image was captured with the Pi camera to produce high-quality images. This research employs a wide range of techniques across the board (from license plate detection to character recognition) to boost the system's speed as much as feasible with negligible overhead. The studies demonstrated how useful image processing tools were used for data logging, and character recognition when combined with vehicles in urban environments. To carry out monitoring and management of the system, a responsive web application was designed for data logging.