Vehicle Speed Estimation System and Automatic License Plate Recognition using Yolov8 and EasyOCR on Traffic Camera Footage

The latest vehicle detection technology has enabled the development of systems that can detect vehicles, estimate speed, and automatically recognize vehicle license plates. In this study, a program was created that uses two different YOLO (You Only Look Once) models for vehicle and license plate detection in the video. The YOLOv8 model is used to detect vehicles, while the special model is used to detect license plates. In the EasyOCR program is a library used for reading vehicle license plates. The program can also detect whether the driver is violating the traffic speed limit. The results of the experiment showed an accuracy level of 91.87% for vehicle speed estimation and 96.87% for automatic license plate recognition. This can be influenced by several factors that can affect the accuracy of vehicle speed estimates and automatic license plate readings. One of these factors that most affects the results is the angle of the shooting.