English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

With the increase in public attention to sports and health, more people are keen to use badminton for fitness, but it is difficult to find professionals for guidance. In the new era, technology is constantly updated, and the artificial badminton sports intelligent computing platform has encountered difficulties in software and hardware engineering technology from data collection to computing programming. Firstly, this paper studies the imaging mechanism and calibration method of the binocular camera and obtains the relationship between the parameters and the position of the lens in the camera. Secondly, a convolutional computing network model Region Proposal Network (RP-ResNet) is established, and the first-stage feature image data collection is performed on the input image. The second step uses an improved pyramid pooling network to pool feature images at different resolutions. Besides, Squeeze-and-Excitation Network (SENet) enhances channel attention, thereby improving the measurement accuracy of small target objects in the network. Finally, a dynamic identification algorithm of badminton hitting based on the sliding window is given, and a real-time identification system of badminton dynamics is implemented on this basis. A statistical system of badminton technical characteristics is established through these badminton dynamic identification methods. According to the test results, the algorithm model system designed here can identify common hitting actions in real-time. The improved Hidden Markov Model (HMM) improves the comprehensive recognition accuracy by 1.25% and shortens the recognition time by 0.07s compared with the traditional HMM. This model will provide an intelligent data analysis platform for badminton, which can be promoted and applied to professional players and coaches. The technical index parameters suitable for the regular development of badminton sports are extracted from the accumulated big data analysis to establish a professional product for intelligent data analysis and auxiliary training of badminton sports.

The Analysis of Technical Characteristics of Badminton for Sports with Neurorobotics under Machine Learning