A wrist-worn gesture recognition device and method with self-repair and self-calibration functions

Abstract

The invention discloses a wristband-type gesture recognition device and method with self-repairing and self-calibration functions, including: a wristband-type array surface electromyography acquisition module and a control core module, wherein: the wristband-type array surface electromyography The acquisition module is used to collect the wrist surface electromyographic signals generated by gestures, and to amplify, filter and digitally sample the signals; the control core module is used for system timing control, signal preprocessing, gesture recognition and control command transmission , including: abnormal signal detection and repair module, electrode calibration module, gesture recognition module, wireless transmission module. The gesture recognition device realizes highly robust recognition of gesture actions through wristband-type array electrode design, abnormal signal detection and repair algorithm, and electrode calibration algorithm. The human-computer interaction technology of gestures has important application value.

Description

technical field [0001] The invention relates to the field of wearable human-computer interaction, in particular to a wrist-band gesture recognition device with high robustness. Background technique [0002] In recent years, gesture recognition has become a mainstream research direction of new human-computer interaction technology. Compared with mechanical devices such as mice and keyboards, gesture interaction is a more natural and human-computer interaction method that is more in line with human habits. With the continuous development of virtual reality technology (VR), gesture recognition and interaction will have greater development prospects. [0003] Electromyography is the electrical signal accompanying muscle contraction, which can reflect neuromuscular activity to a certain extent. Surface electromyography is widely used in the field of human-computer interaction based on gesture recognition due to its non-invasive, non-invasive, and simple operation in measurement...

AI Technical Summary

Problems solved by technology

However, the existing surface electromyography-based gesture recognition devices mostly use single electrodes or discrete electrodes to collect surface electromyography signals. Due to the low density of electrodes, that is, the distance between channels is relatively long, the restoration method using adjacent channels instead of Introduce a certain error, can not guarantee the recognition performance

At the same time, manual participation will increase labor costs and cannot be applied to real-time interaction scenarios

[0005] 2. Due to the different positions and angles of the user wearing the device each time, the electrode offset cannot be avoided during repeated wearing, and the electrode offset will lead to a significant decline in the performance of the classifier or even no longer applicable

Existing gesture recognition devices mostly use a single electrode or discrete electrodes to collect EMG signals, and the electrode density and coverage are low, so it is difficult to effectively combat abnormal signals and electrode offsets

Images