AR与VR技术在冬季体育赛事中的应用分析

The application analysis of augmented reality and virtual reality technology in winter sports events

为了更加清晰和流畅转播冬季体育赛场上的实时画面,设计了一种智能视频分析系统。该系统应用迭代最近点(iterative closest point,ICP)算法对冬季赛场内运动员图像通过点云配准进行实时拼接,并且能够计算出单应性矩阵对原始场景进行增强,增强观众对增强现实(augmented reality,AR)技术与虚拟现实(virtual reality,VR)技术的交互式体验感受。利用平昌冬奥会美国队与韩国队冰球比赛小组赛录像视频,对本智能视频分析系统进行测试,结果表明,本系统可以准确跟踪和识别冬季赛场上运动员,提高了冬季赛场上运动员目标检测的精度。

In order to rebroadcast winter sports competition more clearly and smoothly,an intelligent video analysis system is designed,which can use iterative closest point algorithm to joint real-time athlete images through point cloud matching and calculate the homography matrix to enhance the original scene,and increase AR and VR interactive experience.We tested this algorithm in the intelligent video analysis system by using the video of the pyeongchang winter Olympic Games group between the United States team and the Korea team.The test results showed that this method could track and identify athletes on the winter field,and improve the identification accuracy.