IoV-based collision avoidance by using confidence region

For some IoV-based collision avoidance architectures, it is not necessary that all vehicles have communication ability. Hence, they need some particular designs and extra components. In the literature, one of them uses a camera mounted on the infrastructure at an intersection to realize the collision detection. Consequently, real-time object detection and real-time dynamic prediction are needed. In this paper, by using the concept of confidence region, we propose an interesting method to predict the future position of a vehicle based on a well-known real-time object detection project, YOLOv 3. According to the experimental results, our prototype shows the performance of predicting the future position of a vehicle.