Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sound based gesture recognition method

A technology of gesture recognition and voice, applied in voice input/output, data processing input/output process, instruments, etc., can solve the problems of high cost and constraints

Active Publication Date: 2014-06-25
美声克(成都)科技有限公司
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The application of action recognition in the field of computer interaction has grown more and more active. However, such applications still have high cost, such as Motion detection sensors (e.g.leap motion$70), such as commonly used high-quality cameras (e.g.Microsoft Kinect$200), these devices directly restrict the promotion of motion recognition technology

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
  • Sound based gesture recognition method
  • Sound based gesture recognition method
  • Sound based gesture recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] refer to Figure 9 , a sound-based gesture recognition method, comprising the following steps:

[0055] a) The stereo emits a continuous audio signal with a central frequency of 18KHz, and the microphone receives the audio signal returned from body movement, in which the sampling frequency is 44.1Khz, the size of each sample is 2B, the number of channels of the audio signal is 1, and the size of the sampling queue For 2048 samples.

[0056] b) By calculating the result sampling period T 0 About 46.44ms, by calculating the coverage frequency F of each sample b The boundary is 0KHz to 22.05KHz. After processing, a sampling queue of 1024 points is obtained.

[0057] c) It can be known that f shift It is 0.2KHz, and the limb movement speed under this condition is less than 3.728m / s. Spectrum analysis window queue w can be obtained 1 (x).

[0058] d) Simulation defines the period T of the logic simulate , which requires that T is obtained by calculating simulate Gr...

Embodiment 2

[0064] Hardware environment design: such as figure 2 As shown, a speaker produces a center frequency f 0 The audio signal is received by a microphone that returns the audio signal.

Embodiment 3

[0066] Hardware environment design: Using the characteristics of multi-channel sound, multi-audio can play multi-channel audio with multiple center frequencies. By increasing the number of hardware speakers, add center frequency attributes to simulated messages to achieve more complex gesture recognition. .

[0067] Sound mouse design scheme:

[0068] like image 3 As shown, on the basis of an ordinary USB mouse, a single speaker is embedded to generate an audio signal, and a dual microphone is embedded to receive a return audio signal. The audio signal is generated and received by using the USB itself for power supply and the USB transmission protocol, and the microphone ID is added to the simulated message. Attributes to realize gesture recognition for both hands.

[0069] Microphone array device solution:

[0070] like Figure 4 As shown, a sound box is embedded to generate an audio signal, and multiple microphones are ring-shaped embedded on a slope with a certain radi...

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 discloses a sound based gesture recognition method. A normal microphone and a loudspeaker are used as hardware supports for receiving and transmitting signals, the loudspeaker generates high-frequency sounds difficult for human ears to perceive, the microphone receives sound signals rebounded in limb movements, spectral analysis is conducted by the aid of physical phenomenon Doppler effect of the rebounded sound signals, acquired information of the limb movements is defined as corresponding logic signals, and operations of a computer are controlled by the aid of the logic signals. A brand-new man-computer interaction method is provided in the aspect of computer control, and interesting user experience and interaction feelings can be brought to computer users.

Description

Technical field [0001] The present invention is the field of computer human -computer interaction technology, involving a sound -based gesture recognition method. Background technique [0002] Natural Language Processing is an important direction in the field of computer science and artificial intelligence.It studies various theories and methods that can achieve effective communication between people and computers with natural language.Natural language treatment is a science that integrates linguistics, computer science, and mathematics.Therefore, research in this field will involve natural language, that is, the language of people's daily use, so it is closely related to the research of linguistics, but it is important.Natural language processing is not generally studying natural language, but in the development of computer systems that can effectively realize natural language communication, especially the software system.Therefore, it is part of computer science. [0003] Gestu...

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
IPC IPC(8): G06F3/16G06F3/0487
Inventor 刘鑫刘西耀邹长俊刘东权
Owner 美声克(成都)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com