Research Article
Recognition of Running Gait of Track and Field Athletes Based on Convolutional Neural Network
@INPROCEEDINGS{10.1007/978-3-031-50574-4_16, author={Qiusheng Lin and Jin Wang}, title={Recognition of Running Gait of Track and Field Athletes Based on Convolutional Neural Network}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part II}, proceedings_a={ICMTEL PART 2}, year={2024}, month={2}, keywords={Gait Recognition Athletes Convolution Neural Network Running Gait Feature Extraction Recognition Accuracy}, doi={10.1007/978-3-031-50574-4_16} }- Qiusheng Lin
Jin Wang
Year: 2024
Recognition of Running Gait of Track and Field Athletes Based on Convolutional Neural Network
ICMTEL PART 2
Springer
DOI: 10.1007/978-3-031-50574-4_16
Abstract
With the continuous development of competitive sports, higher requirements have been put forward for the athletic level and technical movements of track and field athletes. Running gait is a key factor that affects the competitive level and technical action of athletes. Therefore, a research on the recognition method of running gait of track and field athletes based on convolutional neural network is proposed. According to the internal noise type of running gait image, the least mean square filtering algorithm is selected as the preprocessing method of running gait image, and it is used to remove the noise of running gait image. Based on this, the LB P feature, Hu moment invariant feature and Haar like feature are extracted as the running gait characteristics, and the convolutional neural network model is designed. With the above designed convolutional neural network model as a tool, the running gait recognition program of track and field athletes is formulated, And determine the calculation formula of the relevant parameters, in order to obtain accurate results of track and field athletes’ running gait recognition. The experimental data show that the maximum accuracy of running gait recognition of track and field athletes obtained by using the proposed method is 94%, which fully proves that the proposed method has better performance in running gait recognition.
