For the Intelligent Transport System (ITS) to function, vehicle classification and location must be completed quickly and precisely. It is difficult to quickly and precisely perceive and recognize vehicle sorts because of the close partition between vehicles in the city and the hindrances perspectives of the image or video picture, counting photos of vehicles. We have attempted to resolve this issue by utilizing the most recent YOLO algorithm. One of the most common uses for speed estimation of moving objects is vehicle speed estimation. It has been demonstrated that the YOLOv8 show can accurately identify moving objects in real-time. Bypassing them through a YOLOv8, vehicles on the street are freed from each video outline. The YOLO show divides the outline into sections, and each section features a vehicle on its claim. A vehicle adaptation identifier follows the outline of the vehicle. The following calculation uses the similarities in the deep highlights to identify and track the question and calculates the profundity features for each bounding box. For perspective, the vehicle's speed can be determined by balancing the pixels per meter. Finally, compare our display's measurements to those of the most advanced models available. We have also added the count of vehicles passed from a particular point. The mean average precision of the algorithm is about 54 percent. The accuracy of Yolo v8 with the deep sort algorithm is around 54 percent which is comparatively higher than the previously proposed algorithms
A Real-Time Vehicle Detection and Speed Estimation Using YOLO V8
18.04.2024
1354163 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Real Time Object Detection using YOLO Algorithm
IEEE | 2022
|Waiting Time Estimation of Hydrogen-Fuel Vehicles with YOLO Real-Time Object Detection
Springer Verlag | 2019
|Embedded Real-Time Vehicle and Pedestrian Detection Using a Compressed Tiny YOLO v3 Architecture
IEEE | 2024
|Real-Time UAV Detection Using an Enhanced YOLO v8 Model
IEEE | 2025
|