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

A static gesture recognition method and device

A gesture and static technology, applied in the field of pattern recognition, can solve the problems of reduced recognition accuracy, lack of rotation invariance, interference of recognition results, etc., and achieve the effect of accurate recognition results

Active Publication Date: 2021-07-13
BENEWAKE BEIJING TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The two-dimensional gesture recognition algorithm is based on color information for segmentation, including skin color detection and edge extraction based on gray value. Its recognition accuracy is often closely related to background complexity, background color and skin color similarity and lighting conditions, and other parts of the body The color information of the two-dimensional gesture recognition algorithm will also interfere with the recognition results, so the accuracy of the two-dimensional gesture recognition algorithm needs to be improved
Neither the KNN algorithm nor the ANN algorithm has rotation invariance, that is, when the gesture rotates at a certain angle, the accuracy of recognition decreases

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 static gesture recognition method and device
  • A static gesture recognition method and device
  • A static gesture recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The static gesture recognition method disclosed in the embodiment of the present application is divided into a training part and a testing part, wherein the purpose of the training part is to train a classifier, and the purpose of the testing part is to use the trained classifier to classify and recognize test gestures.

[0068] In order to solve the problem that the accuracy of the recognition decreases when the gesture has a certain angle of rotation (rotation refers to the rotation of the test gesture at a certain angle compared with the sample), the core point of the technical solution described in this application is that from the gesture The features with rotation invariance are extracted from the depth image, so that the recognition algorithm has rotation invariance.

[0069] The static gesture depth images targeted by the following embodiments include but are not limited to three-dimensional point cloud images.

[0070] The technical solutions in the embodiments...

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 present application provides a static gesture recognition method and device, which acquires a static gesture depth image to be recognized, extracts the foreground in the static gesture depth image to be recognized, extracts rotation invariant features from the target depth image, and rotates The invariance feature is obtained based on the rotation invariance processing of the depth value of the sampling point in the target depth image, and then uses the pre-trained classifier to determine the category of the gesture in the recognized static gesture depth image based on the rotation invariance feature. Because the rotation invariant feature has rotation invariance, the recognition result has rotation invariance, so a more accurate recognition result can be obtained.

Description

technical field [0001] The present application relates to the field of pattern recognition, in particular to a static gesture recognition method and device. Background technique [0002] Vision-based gesture recognition refers to recognizing the meaning represented by the gesture image through the acquired gesture image. Currently, gesture recognition algorithms include two-dimensional gesture recognition algorithms and three-dimensional gesture recognition algorithms. [0003] The two-dimensional gesture recognition algorithm is based on color information for segmentation, including skin color detection and edge extraction based on gray value. Its recognition accuracy is often closely related to background complexity, background color and skin color similarity and lighting conditions, and other parts of the body The color information of the two-dimensional gesture recognition algorithm will also interfere with the recognition results. Therefore, the accuracy of the two-dim...

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): G06K9/00G06K9/46G06N3/04
CPCG06V40/113G06V10/462G06N3/045
Inventor 疏达李远冯强郑凯
Owner BENEWAKE BEIJING TECH CO LTD
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