A gesture recognition method and device based on hyperspectral imaging

A hyperspectral imaging and gesture recognition technology, applied in the field of gesture recognition devices based on hyperspectral imaging, can solve the problems of insufficient accuracy and effectiveness of the recognition system, improve accuracy and effectiveness, eliminate occlusion or dark spots, The effect of reduced distractions

Active Publication Date: 2022-06-07
HEREN KEJI SHENZHEN LLC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of insufficient accuracy and effectiveness of the recognition system based on visible light in the prior art, the present invention discloses a gesture recognition method based on hyperspectral imaging to improve accuracy and effectiveness; Gesture recognition device based on spectral imaging

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
  • A gesture recognition method and device based on hyperspectral imaging
  • A gesture recognition method and device based on hyperspectral imaging
  • A gesture recognition method and device based on hyperspectral imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] See Figures 1 through 5 As shown, the present embodiment discloses a gesture recognition method based on hyperspectral imaging, comprising the following steps S100 to S400:

[0039] S100, through the hyperspectral imaging system to acquire the image of gestures under the joint illumination of the visible light source and the infrared light source, to obtain a hyperspectral image.

[0040] Step S100 such as Figure 2 As shown, the user's hand is in an environment with background influences, using a visible light source and an infrared light source to illuminate together, and then through the hyperspectral imaging system for image acquisition, to obtain a hyperspectral image (that is, an image with multiple channels).

[0041] S200, the hyperspectral image as the target feature fusion processing, the formation of a single-channel image.

[0042] Steps S200 are likewise Figure 2 Shown, which comprises: the hyperspectral image of different bands of the image according to the tar...

Embodiment 2

[0053] With the development of intelligent display devices in the direction of interactive technology more and more advanced, there are currently many TVs or computers and other displays that can be controlled by gestures, including channel switching, volume adjustment, menu settings, or the actions of people or objects in the screen screen. Example TWO discloses a gesture recognition method based on hyperspectral imaging, taking gesture recognition of such intelligent display devices as an example, to collect the image information displayed by the gesture image in the visible and infrared light bands, and to improve the accuracy and effectiveness of the recognition by fusing the target features of the image.

[0054] See Figure 6 , embodiment TWO discloses a gesture recognition method based on hyperspectral imaging, comprising the following steps S110 to S710:

[0055] S110, intelligent display device is initialized, and the hyperspectral imaging system, visible light source and ...

Embodiment 3

[0064] Many video games support somatosensory operation, in the game scenario, the application of example three based on a hyperspectral imaging gesture recognition method, the use of hyperspectral system (hyperspectral camera) to capture the user's hand movements of the video stream; For each frame of video, first remove the band picture with too low brightness, then use SVD to reduce the data size, and then use the convolutional neural network algorithm to identify and select the best classification; If the ambient light is too dark, the picture in the visible light band may be rejected; After SVD processing, the picture information in the non-visible light band will be retained more, and the input characteristics of the convolutional neural network algorithm will be more obvious and the recognition accuracy will be higher.

[0065] as Figure 7 As shown, embodiment THREE discloses a gesture recognition method based on hyperspectral imaging, comprising the following steps S120 to...

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 gesture recognition method and device based on hyperspectral imaging, wherein the gesture recognition method includes: collecting gesture images under the joint illumination of a visible light source and an infrared light source through a hyperspectral imaging system to obtain a hyperspectral image; The multi-channel hyperspectral image is fused with target features to form a single-channel image; the single-channel image is denoised to obtain a denoised image; the denoised image is recognized by image recognition and motion tracking algorithms to obtain gesture recognition results . The present invention can simultaneously collect gesture image information in the visible light band and the infrared light band, and effectively fuse the target features of the multi-channel hyperspectral image in the gesture recognition, so that the contrast of the target feature area is enhanced, thereby effectively performing image segmentation and extracting hand features. Contour information is used for subsequent gesture recognition, which helps to improve the accuracy and effectiveness of gesture recognition.

Description

Technical field [0001] The present invention belongs to the field of gesture recognition technology, specifically relates to a gesture recognition method based on hyperspectral imaging, while involving a gesture recognition device based on hyperspectral imaging. Background [0002] In computer science, gesture recognition is a topic in which mathematical algorithms identify human gestures. Users can use simple gestures to control or interact with the device, allowing the computer to understand human behavior. Its core technologies are gesture segmentation algorithm, gesture analysis algorithm and gesture recognition algorithm. [0003] As technology for image recognition and motion tracking matures, more and more devices can operate and interact with gestures. Compared with traditional mouse and keyboard input, gesture operation is more convenient, the interaction types are more diverse, and the interaction process is more intuitive. There are a number of gesture-controlled comme...

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 Patents(China)
IPC IPC(8): G06V40/20G06V10/82G06N3/04
CPCG06V40/28G06N3/045
Inventor 王星泽李梓彤蒲庆舒远阮思纯徐炜文
Owner HEREN KEJI SHENZHEN LLC
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