Action recognition method and device based on surface electromyographic signal

Abstract

An embodiment of the present invention provides an action recognition method and device based on surface electromyographic signals, the method determines effective surface electromyographic signals according to the surface electromyographic signals of multiple channels by acquiring surface electromyographic signals of multiple channels; and then , determining the frequency of the effective surface electromyography signal, and determining the body movements corresponding to the surface electromyography signals of multiple channels according to the frequency of the effective surface electromyography signal. Since the frequency of the surface electromyography signal has nothing to do with features such as signal strength, the method of this embodiment can significantly improve the accuracy of action recognition based on the surface electromyography signal. Moreover, using the frequency as the identification feature, the user does not need to make large movements, which brings a better experience to the user. In addition, the method of the embodiment of the present invention can also combine the frequency and amplitude characteristics of the surface electromyography signal to identify the corresponding body movements, which can not only improve the recognition accuracy of the surface electromyography signals, but also increase the recognition types of body movements.

Description

technical field [0001] Embodiments of the present invention relate to motion recognition technology, and in particular to a method and device for motion recognition based on surface electromyographic signals. Background technique [0002] Surface electromyography (EMG for short) is a bioelectrical signal related to neuromuscular activity. Surface electromyography can reflect information such as muscle contraction mode and contraction intensity. Different body movements correspond to different surface electromyography signals. , by analyzing the surface electromyography signal, the specific action corresponding to the surface electromyography signal can be identified. Therefore, the surface electromyography signal is widely used in many fields such as clinical medicine, sports medicine, biomedicine and rehabilitation engineering. [0003] In the prior art, the recognition of body movements is carried out using the amplitude characteristics of the surface electromyography sign...

AI Technical Summary

Problems solved by technology

[0004] The method of the prior art has the following problems: Since other actions of the user also generate surface electromyography signals, when the user performs other sports (running, typing, etc.), the generated interference surface electromyography signals and the target surface electromyography signals will occur. superposition, resulting in low recognition accuracy. In addition, the magnitude of the surface electromyography signal is proportional to the magnitude of the user's body movements. In the case of operation, it will make the user feel strenuous

Images