Research Article
High Precision Recognition Method of Basketball Dribbling Posture Based on Lightweight RFID Mobile Authentication Protocol
@INPROCEEDINGS{10.1007/978-3-030-94551-0_10, author={Qiang Huang and Yi-de Liao}, title={High Precision Recognition Method of Basketball Dribbling Posture Based on Lightweight RFID Mobile Authentication Protocol}, proceedings={Advanced Hybrid Information Processing. 5th EAI International Conference, ADHIP 2021, Virtual Event, October 22-24, 2021, Proceedings, Part I}, proceedings_a={ADHIP}, year={2022}, month={1}, keywords={Lightweight RFID Authentication protocol Basketball Dribbling posture Image recognition}, doi={10.1007/978-3-030-94551-0_10} }- Qiang Huang
Yi-de Liao
Year: 2022
High Precision Recognition Method of Basketball Dribbling Posture Based on Lightweight RFID Mobile Authentication Protocol
ADHIP
Springer
DOI: 10.1007/978-3-030-94551-0_10
Abstract
The conventional high-precision recognition method of basketball dribbling posture has distance deviation and angle deviation when recognizing the three-dimensional position of bone points. To solve this problem, a high-precision recognition method of basketball dribbling posture based on lightweight RFID mobile authentication protocol is studied. The camera is placed in the basketball court, the RFID mobile authentication protocol label is arranged, and the basketball dribble posture image is collected. After compressing the image, the image is preprocessed by means of compression, noise suppression and graying, and the scale space of integral image is constructed to recognize the dribble posture edge and contour. Combined with convolution neural network, the precise characteristics of dribble posture are recognized. The results show that, compared with the two conventional methods, the distance deviation of the spatial position of the skeleton points is reduced by 0.007 m and 0.011 m, and the angle deviation is reduced by 2.9° and 4.11° respectively, which improves the attitude recognition accuracy.
