A real-time target detection algorithm is proposed and used in the embedded graphic processing unit (GPU). In view of the lack of computing units and the slow processing speed for an embedded platform, an improved lightweight target detection model is proposed based on the YOLO-V3 (You Only Look Once-Version 3) structure. This model is first trained off-line with vehicle targets and then deployed on the embedded GPU platform to achieve the online prediction. The experimental results show that the processing speed of the proposed method on the embedded GPU platform reaches 23 frame/s for a 640 pixel×480 pixel video.