Research Article
Recognition of Aerobics Movement Posture Based on Multisensor Movement Monitoring
@INPROCEEDINGS{10.1007/978-3-030-94551-0_14, author={Ying Liu and Zhong-xing Huang}, title={Recognition of Aerobics Movement Posture Based on Multisensor Movement Monitoring}, 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={Sensor Mobile monitoring Attitude recognition Feature extraction}, doi={10.1007/978-3-030-94551-0_14} }- Ying Liu
Zhong-xing Huang
Year: 2022
Recognition of Aerobics Movement Posture Based on Multisensor Movement Monitoring
ADHIP
Springer
DOI: 10.1007/978-3-030-94551-0_14
Abstract
In the traditional attitude recognition methods, the final recognition rate is low because of the inadequate processing of the motion attitude data. Therefore, based on the multi-sensor mobile monitoring of aerobics movement posture recognition. In the design process of aerobics movement posture recognition method, first of all, based on multi-sensor movement monitoring, collected aerobics movement posture data. Then in order to improve the recognition rate of aerobics posture, the collected data is preprocessed. Will process the good data, according to the time frequency characteristic complete the data characteristic extraction. Comparing the extracted features with the multi-sensor moving monitoring images, through the multi-level attitude recognition algorithm, the movement attitude recognition of aerobics is finally realized. Experimental results show that the proposed method has a higher recognition rate than the traditional method. Even under the influence of changing factors such as penalty factors and kernel parameters, the proposed method is still predominant.
