Research Article
Dynamic Recognition Method of Track and Field Posture Based on Mobile Monitoring Technology
@INPROCEEDINGS{10.1007/978-3-031-28867-8_25, author={Qiusheng Lin and Lei Han}, title={Dynamic Recognition Method of Track and Field Posture Based on Mobile Monitoring Technology}, proceedings={Advanced Hybrid Information Processing. 6th EAI International Conference, ADHIP 2022, Changsha, China, September 29-30, 2022, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2023}, month={3}, keywords={Monitor Track and field sports Dynamic attitude recognition Gaussian model BP neural network Artificial fish swarm algorithm}, doi={10.1007/978-3-031-28867-8_25} }- Qiusheng Lin
Lei Han
Year: 2023
Dynamic Recognition Method of Track and Field Posture Based on Mobile Monitoring Technology
ADHIP PART 2
Springer
DOI: 10.1007/978-3-031-28867-8_25
Abstract
The recognition technology using conventional sensors or image processing is effective for static gesture recognition, but for dynamic gesture recognition, the moving object can not be tracked in time, resulting in low recognition accuracy and efficiency. In order to optimize the above problems, the dynamic recognition method of track and field posture based on mobile monitoring technology is studied. Set up mobile monitoring equipment in the movement area and the movement track to acquire the data of track and field movement posture. After de-noising the track and field posture data, a Gaussian model is established to segment the image background. Based on the human skeleton model, the motion posture features are extracted. Using BP neural network improved by artificial fish swarm to classify the input movement posture data, the recognition of track and field movement posture is realized. The test results show that the recognition accuracy of the proposed methods is higher than 95%, the recognition efficiency is greatly improved, and it has good practical value.
