首页|基于单目视觉的网球落点定位研究

基于单目视觉的网球落点定位研究

扫码查看
在网球比赛中,目前主要依靠专业设备对网球落点进行定位,成本较高且难以在日常训练中普及,提出了一种基于单目视觉的网球落点定位方法,该方法根据重投影误差筛选标定特征点最优组合,得到相机标定参数,以此建立投影模型,结合网球运动轨迹计算出网球落点的位置信息.实验结果表明,该方法相较于基于张正友标定法和Tsai两步法确定的投影模型的落点定位方法,对网球落点定位的平均误差分别降低了 9.42%和 25.76%.
Research on Tennis Landing Point Measurement Based on Monocular Vision
In tennis competitions,professional equipment is currently mainly used to locate the landing point of tennis balls,which is costly and difficult to widely popularize in daily training.This paper proposes a monocular vision based ten-nis landing point positioning method.This method filters and calibrates the optimal combination of feature points based on the re projection error,obtains camera calibration parameters,and establishes a projection model to calculate the position information of the tennis landing point combined with the tennis movement trajectory.The experimental results show that the average error of the method in this paper is 9.42%and 25.76%lower than that of the method based on the projection model determined by Zhengyou Zhang calibration method and Tsai two-step method,respectively.

monocular visioncamera calibrationlanding point positioning

顾潇洋、宗志伟

展开 >

上海大学通信与信息工程学院,上海 200444

上海大学体育学院,上海 200444

单目视觉 相机标定 落点定位

2024

工业控制计算机
中国计算机学会工业控制计算机专业委员会 江苏省计算技术研究所有限责任公司

工业控制计算机

影响因子:0.258
ISSN:1001-182X
年,卷(期):2024.37(4)
  • 8