Unlock instant, AI-driven research and patent intelligence for your innovation.

Gesture recognition method and device based on depth image

A depth image and gesture recognition technology, applied in the field of gesture recognition, can solve problems such as being easily affected by light, and achieve the effect of robust performance and small light conditions

Inactive Publication Date: 2017-08-25
RICOH KK
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is also susceptible to the influence of light

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 recognition method and device based on depth image
  • Gesture recognition method and device based on depth image
  • Gesture recognition method and device based on depth image

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0030] 2.1 The overall flow of the gesture recognition method

[0031] 2.2. Acquisition of 3D motion trajectory

[0032] 2.3. Hand gesture recognition based on 3D motion trajectory

[0033] 2.4. Motion feature extraction of 3D motion trajectory

[0034] 2.5. Predetermined gesture recognition based on motion features of 3D motion trajectory

[0035] 2.6. Gesture recognition using sliding window with variable window size

[0036] 3. The second embodiment of the gesture recognition method

[0037] 3.1 Overall flow of the gesture recognition method of the second embodiment

[0038] 3.2. Validate predetermined gestures against an anthropometry model

[0039] 4. How to start the human-computer interaction system

[0040] 5. Gesture recognition device based on depth image

[0041] 6. System hardware configuration

[0042] 7. Summary

[0043] 1. Examples of application scenarios

[0044] figure 1 A schematic diagram schematically shows a scenario where a gesture recognition...

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

Provided are a gesture recognition method based on a depth image, a gesture recognition device, and a method and device for starting a human-computer interaction system. The gesture recognition method may include: based on the depth image sequence including the hand region, detecting the three-dimensional movement trajectory of the hand candidate region; and recognizing a predetermined gesture according to the three-dimensional movement trajectory of the hand candidate region. The above-mentioned gesture recognition method and device in the embodiments of the present invention make full use of the motion information in the continuous recognition images; since the skin color model is not used, but the temporal and spatial domain motion information and continuous depth value change information of continuous images are used for gesture recognition, therefore The performance of the gesture recognition method is relatively robust, and it is less affected by the lighting conditions; because the gesture recognition is based on the motion trajectory, it can be used in a relatively long distance range.

Description

technical field [0001] The present invention generally relates to gesture recognition, and more particularly relates to a gesture recognition method and device based on a depth image. Background technique [0002] Some gesture recognition techniques based on image processing have been proposed. [0003] In the US patent "US7340077B2", a gesture recognition system based on a depth sensor is proposed. The method conducts gesture recognition on the combination of gestures within a certain time range, mainly for the shape, position and direction of the recognized part, and finally controls the relevant electrical equipment through the recognized gestures. This method mainly uses static image information for recognition, and loses a large amount of motion information in continuous video images. In addition, gesture recognition is mainly based on combined gestures, so the user must perform multiple gesture modes to complete a gesture, which is not very convenient for the user to...

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): G06K9/00G06F3/01
Inventor 梁玲燕赵颖
Owner RICOH KK