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

Gesture identification method based on depth information

A technology of depth information and gesture recognition, applied in the field of gesture recognition based on depth information, can solve problems such as interference, kinect cannot adapt to changes in light, etc., and achieve high real-time performance and small calculation

Inactive Publication Date: 2012-11-21
HANGZHOU DELAN TECH CO LTD
View PDF5 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Microsoft's kinect cannot adapt to changes in light. Outdoor sunlight and indoor switching lights will interfere. It is only used in indoor scenes with stable light sources.

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
  • Gesture identification method based on depth information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described below in conjunction with accompanying drawing.

[0018] Step 1: Obtain a real-time depth image from a binocular camera that can output depth information, and use a mixed Gaussian background modeling method for the depth image to obtain a background image. Since the depth calculation method is susceptible to occlusion, distortion, etc., resulting in noise and holes in the depth image, the mixed Gaussian method here uses three Gaussian kernels. which is figure 1 The steps of building a background model.

[0019] Step 2: Use the difference between the background image and the current image to detect the foreground area. corresponding figure 1 motion detection.

[0020] Step 3: Utilize the dual background update method to update the established background image to reduce the impact on the calculation error of the depth image.

[0021] Step 4: Collect human samples and non-human samples, and use random forest classifier t...

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 a gesture identification method based on depth information. The existing method has certain problems in the practical application environment and user experience. Firstly, a real-time depth image is acquired, a background image is acquired after background modeling, and a foreground area is detected by using the background image and the current image as a difference. Secondly, the built background image is updated and an independent human body area is extracted, then, a hand area and outline information are detected from each independent human body area, and the movement track of the hands tracking is obtained. Finally, the movement track is modeled by using a hidden Markov model to identify the gesture. The method can adapt to interference of skin color changes, is barely affected by factors such as distance, illumination, shading, movement and the like in the indoor environment, and is small in arithmetic calculation amount and high in real-time performance.

Description

technical field [0001] The invention belongs to the technical field of human-computer interaction, and relates to a gesture recognition method based on depth information. Background technique [0002] Gesture recognition technology has achieved rapid development in recent years. Gesture recognition based on single camera, gesture recognition based on dual cameras, and Microsoft's kinect gesture recognition have successively appeared in home appliance control, game control and other application fields. However, there are certain problems in the actual application environment and user experience. exist: [0003] When multiple human bodies or gestures under a single camera are occluded, the hands cannot be positioned accurately, resulting in a low recognition rate; such as patents "Static Gesture Recognition Method Based on Vision", "Dynamic Gesture Recognition Method in Interactive Systems", etc.; [0004] The methods under single-camera and dual-camera mainly use the skin c...

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): G06K7/00
Inventor 尚凌辉张兆生贺磊盈余天明高勇
Owner HANGZHOU DELAN 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