Peng, Min
(School of Computer Science and Information Engineering, Hefei University of Technology,Hefei,China)
,
Zhang, Zhong
(School of Computer Science and Information Engineering, Hefei University of Technology,Hefei,China)
,
Zhou, Qingfeng
(School of Electrical Engineering & Intelligentization, Dongguan University of Technology,Dongguan,China)
In the basketball training, statistical data of basketball footwork can be used to improve training level. However, most basketball motion recognition systems are with high cost, and the recognition of footwork is often overlooked. In this paper, we propose a system to recognize basketball footwork ...
In the basketball training, statistical data of basketball footwork can be used to improve training level. However, most basketball motion recognition systems are with high cost, and the recognition of footwork is often overlooked. In this paper, we propose a system to recognize basketball footwork using smart insoles. The system collects data through the three-axis accelerometer and three-axis angular velocity meter embedded in smart insoles. Then, five kinds of basic basketball footwork such as sideslip step, back step, cross step, jab step and jump step can be recognized. In this paper, K-Nearest Neighbors (KNN), Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) are used for footwork recognition. The experimental results show that the proposed system can recognize five kinds of basketball footwork effectively.
In the basketball training, statistical data of basketball footwork can be used to improve training level. However, most basketball motion recognition systems are with high cost, and the recognition of footwork is often overlooked. In this paper, we propose a system to recognize basketball footwork using smart insoles. The system collects data through the three-axis accelerometer and three-axis angular velocity meter embedded in smart insoles. Then, five kinds of basic basketball footwork such as sideslip step, back step, cross step, jab step and jump step can be recognized. In this paper, K-Nearest Neighbors (KNN), Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) are used for footwork recognition. The experimental results show that the proposed system can recognize five kinds of basketball footwork effectively.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.