Micro-gesture detection method contributing to non-contact human-computer interaction

A technology of human-computer interaction and gesture detection, applied in the field of gesture detection, can solve the problems of ignoring the effect of gestures and costing a lot of money, and achieve the effect of improving accuracy and ensuring real-time performance

Pending Publication Date: 2021-01-01
广州宇中网络科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In these studies, the introduction of intelligent physical devices requires replacing the current infrastructure, costing a lot of money
Research using artificial intelligence technology is mainly focused on voice interaction, ignoring the role of gestures

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
  • Micro-gesture detection method contributing to non-contact human-computer interaction
  • Micro-gesture detection method contributing to non-contact human-computer interaction
  • Micro-gesture detection method contributing to non-contact human-computer interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0072] A micro-gesture detection method conducive to contactless human-computer interaction, comprising the following steps:

[0073] 1): Use the camera to collect video data, and the default writing posture of the initial video frame is to raise a finger;

[0074] 2): For the video frame collected in step 1, preprocessing is performed; based on the video data in step 1, the video frame image is obtained; the video image is denoised;

[0075] 3): Initialize the background modeling based on the following mixed Gaussian distribution probability density function;

[0076]

[0077] 4): Every new pixel X t Compare the first K Gaussian distributions according to the following formula; |X t -μ i,t-1 |≤2.5*σ i,t-1 ;

[0078] If the mean deviation from the Gaussian distribution is within 2.5σ, it means that the new pixel matches the Gaussian distribution, if not, replace the minimum distribution;

[0079] 5): Define the image gray mean value change rate R t and image skin col...

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

A micro-gesture detection method beneficial to non-contact man-machine interaction comprises the following steps of: using a camera for collecting video data, preprocessing collected video frames, using an improved Gaussian mixture algorithm for background modeling, segmenting a foreground, extracting gestures in the foreground through an HSV color space, and recognizing an obtained gesture contour; positioning a gravity center point and a writing point, tracking the writing point, and recording a writing track curve; performing gesture detection by using a gray histogram, establishing a Gaussian mixture model by using the gray histogram, comparing the ratio of the overall gray value to the skin color value, and controlling the background model updating rate based on the image gray changerate and the skin color change rate, so that the accuracy of the detection system is improved on the premise of ensuring the real-time performance.

Description

technical field [0001] The invention relates to a gesture detection method, in particular to a micro-gesture detection method conducive to contactless human-computer interaction. Background technique [0002] Contactless service is a new type of service model, which can carry out daily prevention of contact infectious diseases and ensure the safety of users as much as possible. The contactless service model extends its tentacles to all aspects of social production and life. How to abandon the keyboard, mouse or point-touch interaction and realize contactless human-computer interaction has gradually attracted people's attention. In recent years, the development of artificial intelligence technology has provided theoretical and equipment support for exploring new human-computer interaction methods. Driven by user needs, it has become an inevitable trend to realize intelligent human-computer interaction in a non-contact mode. [0003] Current research related to touchless HC...

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): G06T7/00G06T7/136G06T7/194G06T5/00G06T5/30G06T5/40
CPCG06T7/0002G06T7/194G06T7/136G06T5/002G06T5/30G06T5/40G06T2207/10016
Inventor 龙建华吴鹏
Owner 广州宇中网络科技有限公司
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