Intelligent gesture recognition method and system based on electrical measurement

A gesture recognition and intelligent technology, applied in the field of intelligent gesture recognition, can solve problems such as low recognition rate, limited use conditions, complex design, etc.

Pending Publication Date: 2022-05-20
BEIJING MECHANICAL EQUIP INST
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above analysis, the embodiment of the present invention aims to provide a smart gesture recognition method and system based on electrical measurement to solve the problems of complex design, limited use conditions and low recognition rate in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent gesture recognition method and system based on electrical measurement
  • Intelligent gesture recognition method and system based on electrical measurement
  • Intelligent gesture recognition method and system based on electrical measurement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] A specific embodiment of the present invention discloses a smart gesture recognition method based on electrical measurement, such as figure 1 shown, including the following steps:

[0096]S1. Arranging a distributed electrode sensor array on the user's hand, and energizing each electrode in the array; optionally, the electrode sensor array can be arranged on the user's finger or wrist.

[0097] S2. When the user's hand moves, the distributed sensor array collects voltage signals at various points on the skin of the user's hand;

[0098] S3. Preprocessing the voltage signals of the above points respectively to obtain the effective voltage amplitude and phase of each point;

[0099] S4. Use the effective voltage amplitude and phase of the above points as input variables, and input them into the deep neural network trained in advance to obtain the predicted probability of each type of gesture;

[0100] S5. The predicted probability of each type of gesture mentioned above...

Embodiment 2

[0104] Based on the optimization in Example 1, in step S1, the distributed electrode sensor array includes N flexible electrode sensors arranged at equal intervals on the wristband; each flexible electrode sensor has the same size, specification, and material. The specifications refer to the shape, sensitivity and other indicators are consistent.

[0105] Exemplarily, eight flexible electrode sensors can be evenly arranged on the wristband, and each flexible electrode sensor is at the same distance from the skin, as shown in figure 2 shown.

[0106] At present, the types of gestures that have been distinguished are relaxation, fist, open, left bend and right bend, and one of them can be obtained through deep neural network + classifier, such as image 3 shown.

[0107] Preferably, step S3 further includes:

[0108] S31. Amplify, filter, and AD convert the weak electrical signal obtained by each flexible electrode sensor electrode on the wristband in turn to obtain the peak...

Embodiment 3

[0148] The present invention also discloses an intelligent gesture recognition system corresponding to Embodiment 1, including a distributed electrode sensor array, a preprocessing module, a data processing and control module, and a multiplex gate module, such as Figure 4 shown. Wherein, the output end of the distributed electrode sensor array is connected to the input end of the data processing and control module through the preprocessing module, and the control end of the data processing and control module is connected to each electrode of the distributed electrode sensor array through the multi-channel gate module .

[0149] The distributed electrode sensor array is used to collect voltage signals at various points on the user's hand skin and transmit them to the preprocessing module.

[0150] The pre-processing module is used to pre-process the voltage signal of each point on the skin of the user's hand, obtain the effective voltage amplitude and phase of each point, and...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an intelligent gesture recognition method and system based on electrical measurement, belongs to the technical field of intelligent gesture recognition, and solves the problems of complex design, limited use conditions and too low recognition rate in the prior art. The method comprises the following steps: arranging a distributed electrode sensor array, and electrifying each electrode in the array; when the hand of the user acts, voltage signals of all points on the skin of the hand of the user are collected through the distributed sensor array; preprocessing the voltage signal of each point to obtain the effective voltage amplitude and phase of each point; inputting the effective voltage amplitude and the phase of each point into a pre-trained deep neural network to obtain a prediction probability of each type of gestures; and inputting the prediction probability of each type of gestures into a pre-trained classifier to obtain a current gesture type. According to the invention, electrical measurement and deep learning are combined for gesture recognition, the recognition accuracy is improved, the equipment cost is reduced, and the portability of the equipment is improved.

Description

technical field [0001] The invention relates to the technical field of intelligent gesture recognition, in particular to an electrical measurement-based intelligent gesture recognition method and system. Background technique [0002] With the continuous development of human-computer interaction technology, gesture recognition method, as an important research direction, has become a key technology that cannot be ignored in the field of smart device control. Users can control the device through simple gestures, or interact with the device, or let the computer understand human behavior. [0003] Existing gesture recognition methods can be divided into vision-based gesture recognition methods and wearable gesture recognition methods according to different input devices. The former needs to be implemented in a specific, unobstructed environment. The acquisition of gesture images depends on the external environment, and the recognition effect is easily affected by light and compl...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/11A61B5/053A61B5/00
CPCA61B5/1118A61B5/1121A61B5/053A61B5/6825A61B5/7264A61B5/7267A61B5/7235A61B5/7271A61B5/7275
Inventor 刘宗毓王利周通李兴浩
Owner BEIJING MECHANICAL EQUIP INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap