摘要
为了提升体育网球错误技术动作识别能力,提出了基于机器视觉技术的体育网球错误技术动作识别方法。根据人体五大部分的划分结果,建立了人体的躯干、左臂、右臂、左腿、右腿在三维空间坐标内的肢体向量,依据人体五部分骨骼关节之间的距离,提取体育网球错误技术动作特征,利用机器视觉技术跟踪网球运动目标,获取网球运动员的活动区域,结合体育网球错误技术动作识别区域的质心坐标计算结果,生成错误技术动作跟踪图像,通过计算体育网球错误技术动作描述符设计识别流程,实现体育网球错误技术动作识别。实验结果表明,本文方法不仅可以提高体育网球错误技术动作识别的召回率,还可以提升识别精准率,从而提高了体育网球错误技术动作识别能力。
In order to improve the ability of sports tennis error technical action recognition,this paper proposes a sports tennis error technical action recognition method based on machine vision technology.According to the division results of the five parts of human body,the body vectors of the body's trunk,left arm,right arm,left leg and right leg in three-dimensional space coordinates are established.According to the distance between the five parts of human body bone joints,the wrong technical action characteristics of sports tennis are extracted,and the tennis movement target is tracked by machine vision technology,and the activity area of tennis players is obtained,through calculating the centroid coordinates of the error technical action recognition area,the tracking image of the wrong technical action is generated,and the identification process is designed by calculating the sports tennis error technical action descriptor to realize the sports tennis wrong technical action recognition.The experimental results show that this method can not only improve the recall rate of sports tennis error technical action recognition,but also improve the recognition accuracy rate,thus improving the ability of sports tennis error technical action recognition.
作者
张伟
ZHANG Wei(Anhui Technical College of Mechanical and Electrical Engineering,Anhui Wuhu 241002,China)
出处
《齐齐哈尔大学学报(自然科学版)》
2021年第6期26-30,共5页
Journal of Qiqihar University(Natural Science Edition)
关键词
机器视觉技术
体育网球
错误技术动作
特征提取
动作识别
machine vision technology
sports tennis
wrong technical action
feature extraction
action recognition