基于卡尔曼滤波的网球发球最佳击球点预测系统
|
摘要
针对传统系统缺少最小方差估算步骤,容易受到信号干扰影响,存在预测精准度较低的问题,提出基于卡尔曼滤波的网球发球最佳击球点预测系统。根据系统硬件结构框图,设计预测感知模块,获取可读与不可读信息。为了使系统只传输可读信息,设计闭合开关,并在硬件末端设置客户端模块,显示预测结果,改善信号干扰问题。采用最小方差估计算法对硬件中的预测感知模块进行软件功能设计,并根据卡尔曼滤波原理进行多次迭代处理,获取最佳击球点滤波输出值。实验结果表明,该系统预测精准度最高可达到82%,能够准确找出最佳击球点。
The traditional system lacks the minimum variance estimation step,and is easily affected by signal interference,which may result in low prediction accuracy. A Kalman filtering based best hitting point prediction system of tennis serve is proposed to solve this problem. According to the structure diagram of the system hardware,the predictive perceptive module is designed to obtain the readable and unreadable information. The closed switch is designed to make the system can only transmit the readable information,and the client module is set on the hardware terminal to display the prediction results,so as to improve the signal interference. The minimum variance estimation algorithm is used to design the software function of the predictive perception module in hardware,and the multi-iteration processing based on Kalman filtering principle is adopted to obtain the best filtering output value of the hitting point. The experimental results show that the prediction accuracy of the system can reach up to 82%,and the system can find out the best hitting point accurately.
The traditional system lacks the minimum variance estimation step,and is easily affected by signal interference,which may result in low prediction accuracy. A Kalman filtering based best hitting point prediction system of tennis serve is proposed to solve this problem. According to the structure diagram of the system hardware,the predictive perceptive module is designed to obtain the readable and unreadable information. The closed switch is designed to make the system can only transmit the readable information,and the client module is set on the hardware terminal to display the prediction results,so as to improve the signal interference. The minimum variance estimation algorithm is used to design the software function of the predictive perception module in hardware,and the multi-iteration processing based on Kalman filtering principle is adopted to obtain the best filtering output value of the hitting point. The experimental results show that the prediction accuracy of the system can reach up to 82%,and the system can find out the best hitting point accurately.
引文
[1]李春来,张海宁,杨立滨,等.基于无迹卡尔曼滤波神经网络的光伏发电预测[J].重庆大学学报,2017,40(4):54-61.LI Chunlai,ZHANG Haining,YANG Libin,et al.Photovoltaic power forecasting based on unscented Kalman filtering neural network[J].Journal of Chongqing University(natural science edition),2017,40(4):54-61.
[2]刘鹏华,姚尧,梁昊,等.耦合卡尔曼滤波和多层次聚类的中国PM2.5时空分布分析[J].地球信息科学学报,2017,19(4):475-485.LIU Penghua,YAO Rao,LIANG Hao,et al.Analyzing spatiotemporal distribution of PM2.5 in China by integrating Kalman filter and multi-level clustering[J].Journal of geo-information science,2017,19(4):475-485.
[3]辜小花,王坎,李燕,等.基于演化模型偏好多目标优化的智能采油辅助决策支持[J].机械工程学报,2017,53(13):159-169.GU Xiaohua,WANG Kan,LI Yan,et al.The intelligent oil extraction auxiliary decision based on evolution model and preference driven multi-objective optimization[J].Journal of mechanical engineering,2017,53(13):159-169.
[4]张治远.基于三维图像的运动员起跑动作误差预测仿真[J].计算机仿真,2017,34(8):412-416.ZHANG Zhiyuan.Error prediction and simulation of athlete′s starting action based on 3D image[J].Computer simulation,2017,34(8):412-416.
[5]杜正聪,邓寻.基于自适应遗传算法的粒子滤波器[J].成都理工大学学报(自然科学版),2017,44(5):636-640.DU Zhengcong,DENG Xun.Particle filter based on adaptive genetic algorithm[J].Journal of Chengdu University of Technology(science&technology edition),2017,44(5):636-640.
[6]王坎,辜小花,高论,等.基于UPFNN的油田机采工艺动态演化建模[J].现代电子技术,2017,40(5):109-114.WANG Kan,GU Xiaohua,GAO Lun,et al.UPFNN-based dynamic evolution modeling of oil field mechanical plucking technology[J].Modern electronics technique,2017,40(5):109-114.
[7]ZHENG Liang.Research on computer vision based trajectory tracking of rhythmic gymnastics[J].Modern electronics technique,2017,40(19):19-24.
[8]彭继慎,吕东东,宋立业,等.基于非线性STUKF滤波器和ESN算法的耦合预测模型[J].传感技术学报,2017,30(7):1029-1034.PENG Jishen,LüDongdong,SONG Liye,et al.Prediction model of coupled algorithm based on nonlinear STUKF and ESN[J].Chinese journal of sensors and actuators,2017,30(7):1029-1034.
[9]王炜,张国建,姜鸣,等.调度侧风电功率预测系统设计与应用[J].电网与清洁能源,2017,33(5):79-82.WANG Wei,ZHANG Guojian,JIANG Ming,et al.Design and application of wind power forecasting system at dispatching center[J].Advances of power system&hydroelectric engineering,2017,33(5):79-82.
[10]高学攀,廖士中.基于贝叶斯网络的林火概率预测系统设计与实现[J].计算机工程与应用,2017,53(13):246-251.GAO Xuepan,LIAO Shizhong.Design and implementation of forest fire probability prediction system based on Bayesian network[J].Computer engineering and applications,2017,53(13):246-251.
[11]施建俊,李庆亚,张琪,等.基于Matlab和BP神经网络的爆破振动预测系统[J].爆炸与冲击,2017,37(6):1087-1092.SHI Jianjun,LI Qingya,ZHANG Qi,et al.Forecast system for blasting vibration velocity peak based on Matlab and BP neural network[J].Explosion and shock waves,2017,37(6):1087-1092.
[12]GUO Zhun,ZHOU Tianjun.The simulation of stratocumulus and its impacts on SST:based on the IAP near-term climate prediction system[J].Advances in earth science,2017,32(4):373-381.
[2]刘鹏华,姚尧,梁昊,等.耦合卡尔曼滤波和多层次聚类的中国PM2.5时空分布分析[J].地球信息科学学报,2017,19(4):475-485.LIU Penghua,YAO Rao,LIANG Hao,et al.Analyzing spatiotemporal distribution of PM2.5 in China by integrating Kalman filter and multi-level clustering[J].Journal of geo-information science,2017,19(4):475-485.
[3]辜小花,王坎,李燕,等.基于演化模型偏好多目标优化的智能采油辅助决策支持[J].机械工程学报,2017,53(13):159-169.GU Xiaohua,WANG Kan,LI Yan,et al.The intelligent oil extraction auxiliary decision based on evolution model and preference driven multi-objective optimization[J].Journal of mechanical engineering,2017,53(13):159-169.
[4]张治远.基于三维图像的运动员起跑动作误差预测仿真[J].计算机仿真,2017,34(8):412-416.ZHANG Zhiyuan.Error prediction and simulation of athlete′s starting action based on 3D image[J].Computer simulation,2017,34(8):412-416.
[5]杜正聪,邓寻.基于自适应遗传算法的粒子滤波器[J].成都理工大学学报(自然科学版),2017,44(5):636-640.DU Zhengcong,DENG Xun.Particle filter based on adaptive genetic algorithm[J].Journal of Chengdu University of Technology(science&technology edition),2017,44(5):636-640.
[6]王坎,辜小花,高论,等.基于UPFNN的油田机采工艺动态演化建模[J].现代电子技术,2017,40(5):109-114.WANG Kan,GU Xiaohua,GAO Lun,et al.UPFNN-based dynamic evolution modeling of oil field mechanical plucking technology[J].Modern electronics technique,2017,40(5):109-114.
[7]ZHENG Liang.Research on computer vision based trajectory tracking of rhythmic gymnastics[J].Modern electronics technique,2017,40(19):19-24.
[8]彭继慎,吕东东,宋立业,等.基于非线性STUKF滤波器和ESN算法的耦合预测模型[J].传感技术学报,2017,30(7):1029-1034.PENG Jishen,LüDongdong,SONG Liye,et al.Prediction model of coupled algorithm based on nonlinear STUKF and ESN[J].Chinese journal of sensors and actuators,2017,30(7):1029-1034.
[9]王炜,张国建,姜鸣,等.调度侧风电功率预测系统设计与应用[J].电网与清洁能源,2017,33(5):79-82.WANG Wei,ZHANG Guojian,JIANG Ming,et al.Design and application of wind power forecasting system at dispatching center[J].Advances of power system&hydroelectric engineering,2017,33(5):79-82.
[10]高学攀,廖士中.基于贝叶斯网络的林火概率预测系统设计与实现[J].计算机工程与应用,2017,53(13):246-251.GAO Xuepan,LIAO Shizhong.Design and implementation of forest fire probability prediction system based on Bayesian network[J].Computer engineering and applications,2017,53(13):246-251.
[11]施建俊,李庆亚,张琪,等.基于Matlab和BP神经网络的爆破振动预测系统[J].爆炸与冲击,2017,37(6):1087-1092.SHI Jianjun,LI Qingya,ZHANG Qi,et al.Forecast system for blasting vibration velocity peak based on Matlab and BP neural network[J].Explosion and shock waves,2017,37(6):1087-1092.
[12]GUO Zhun,ZHOU Tianjun.The simulation of stratocumulus and its impacts on SST:based on the IAP near-term climate prediction system[J].Advances in earth science,2017,32(4):373-381.