Design and Implementation of Target Detection System Based on High Performance FPGA and GPU

In this article, we have proposed and designed an object detection system based on Programmable Logic and GPU processors, on which Yolo V8 image detection algorithm is implemented. Our proposed system is capable of real-time image acquisition from high-speed fiber optic SRIO interface and achieve detection performance and 1920x1080@30fps, which means it can detect object in real time. In addition, this system can present the detection results through HDMI interface.