A method and system for online gesture recognition based on surface electromyographic signals

Abstract

The invention belongs to the field of artificial intelligence technology, and discloses an online recognition method and system for gesture actions based on surface electromyographic signals, which collect the surface muscles of the four channels of triceps, anconeus, biceps, and brachioradialis in real time. Electrical signal; then perform wavelet threshold denoising processing; extract the root mean square (RMS) feature of the processed signal and the first 4-order AR model parameter features, and finally use the SVM voting method and clustering to jointly identify real-time actions. Recognition every 0.05s. The number of training samples for each action is only 10, the number of samples and the number of feature types are small, which is convenient for real-time recognition; the joint discrimination of SVM voting method and clustering thinking can improve the accuracy of recognition; the application of clustering thinking can be used to a certain extent The identification of abnormal actions was rejected.

Description

An online gesture recognition method and system based on surface electromyography signals technical field The invention belongs to technical field of artificial intelligence, relate in particular to a kind of gesture action online based on surface electromyography signal Identification method and system. Background technique [0002] At present, the closest prior art: [0003] With the development of science and technology, the research on gesture recognition technology has become a hot topic. The application of the technology has also begun to penetrate into all aspects of people's lives, which is a sign that a technology is becoming popular. Surface EMG The application areas are mainly in human-computer interaction and prosthetic control. In the traditional gesture recognition based on the surface electromyography signal, a structure similar to speech recognition is adopted, that is, the signal acquisition Set-Active Segment Detection-Feature Extraction-Classifica...

AI Technical Summary

Problems solved by technology

[0018] Aiming at the problems of weak algorithm robustness and difficult balance between real-time and accuracy in the traditional online gesture recognition algorithm, the present invention provides an online gesture recognition method and system based on surface electromyography signals

Images