Computer simulation based on digital twin is an essential process when designing self-driving cars. However, designing a simulation program that is exactly equivalent to real phenomena can be arduous and cost-ineffective because too many things must be implemented. In this paper, we propose the method using the online game GTA5 (Grand Theft Auto5), as a groundwork for autonomous vehicle simulation. As GTA5 has a variety of well-implemented objects, people, and roads, it can be considered a suitable tool for simulation. By using OpenCV (Open source computer vision) to capture the GTA5 game screen and analyzing images with YOLO (You Only Look Once) and TensorFlow based on Python, we can build a quite accurate object recognition system. This can lead to writing of algorithms for object avoidance and lane recognition. Once these algorithms have been completed, vehicles in GTA5 can be controlled through codes composed of the basic functions of autonomous driving, such as collision avoidance and lane-departure prevention. In addition, the algorithm tested with GTA5 has been implemented with a programmable RC car (Radio control car), DonkeyCar, to increase reliability. By testing those algorithms, we can ensure that the algorithms can be conducted in real time and they cost low power and low memory size. Therefore, we have found a way to approach digital twin technology one step more easily.

Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved.