基于FSR和陀螺仪的足球运动腿部姿态实时检测技术

Real-Time Detection Technique of Football Posture Based on FSR and Gyroscope

针对足球运动姿态变化快导致腿部姿态检测精度低以及实时性差的缺陷,提出基于FSR和陀螺仪的足球运动腿部姿态实时检测技术。将FSR与陀螺仪分别安装于足球运动员腿部,利用FSR与陀螺仪所采集压力以及角速度信息通过离散度所获取阈值判断足球运动员腿部是否为运动状态。足球运动员腿部为运动状态时,提取FSR传感器以及陀螺仪传感器所采集数据的时域特征以及频域特征,并将所采集时域特征以及频域特征发送至支持向量机分类器作为训练样本,通过支持向量机分类器实现足球运动腿部姿态实时检测。实验研究结果表明,该方法检测不同足球运动腿部姿态平均检测时间低于500 ms,准确率均高于99.5%,平均召回率高达99%以上。

In view of the shortcomings of low accuracy and poor real-time performance caused by the fast change of soccer posture,a real-time detection technology of soccer leg posture based on FSR and gyroscope was proposed.FSR and gyroscope were installed on the legs of football players.The pressure and angular velocity information collected by FSR and gyroscope were used to determine whether the leg movement of football players was in the state of motion through the threshold value obtained by dispersion.When the legs of football players were in the state of motion,the time-domain and frequency-domain features of the data collected by FSR sensors and gyroscope sensors were extracted.The time-domain and frequency-domain features were sent to SVM classifier as training samples,and the real-time detection of soccer leg posture was realized by SVM classifier.The experimental results showed that the average detection time was less than 500 ms,the accuracy higher than 99.5%,and the average recall rate over 99%.