KR20170010288A - Multi kinect based seamless gesture recognition method - Google Patents

Multi kinect based seamless gesture recognition method Download PDF

Info

Publication number
KR20170010288A
KR20170010288A KR1020150102072A KR20150102072A KR20170010288A KR 20170010288 A KR20170010288 A KR 20170010288A KR 1020150102072 A KR1020150102072 A KR 1020150102072A KR 20150102072 A KR20150102072 A KR 20150102072A KR 20170010288 A KR20170010288 A KR 20170010288A
Authority
KR
South Korea
Prior art keywords
kinect
gesture
user
gesture recognition
recognition method
Prior art date
Application number
KR1020150102072A
Other languages
Korean (ko)
Inventor
이동우
서정화
김대현
Original Assignee
주식회사 나무가
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 나무가 filed Critical 주식회사 나무가
Priority to KR1020150102072A priority Critical patent/KR20170010288A/en
Publication of KR20170010288A publication Critical patent/KR20170010288A/en

Links

Classifications

    • G06K9/00335—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The present invention relates to a Multi Kinect based seamless gesture recognition method capable of effectively recognizing the gesture of a user without using a blind spot by using a plurality of Kinect, one of the Depth sensors. The objective of the prevent invention is to provide a Multi Kinect based seamless gesture recognition method capable of recognizing multiple users rather than a single user by using a plurality of Kinect, one of Depth sensors, and to provide a desired content without a blind spot in a recognition range.

Description

[0001] MULTI KINECT BASED SEAMLESS GESTURE RECOGNITION METHOD [0002]

The present invention relates to a Multi Kinect-based seamless gesture recognition method that can effectively recognize a user without a blind spot by using a plurality of Kinect, which is one of the depth sensors, as a gesture of a user.

Depth sensors are widely used for the convenience of users in kiosks in which information is easily accessible to the user, among information transmission devices installed in major public facilities. In the case of a kiosk installed in a public facility, since a plurality of users use a depth sensor, a single depth sensor can not recognize multiple users and has a problem that a blind spot of the recognition range occurs.

In order to solve the above problems, in the present invention, it is possible to recognize not only a single user but a plurality of users by using a plurality of Kinect, which is one of the Depth sensors, instead of one, and recognize a user's gesture The object of the present invention is to provide a Multi Kinect-based seamless gesture recognition method capable of providing contents.

In order to achieve the above object, a Multi Kinect-based seamless gesture recognition method according to the present invention includes:

It is possible to match some degree using the Alternative ViewPointDepthTolmage () method, but there is a limit, and more precise adjustments require more sophisticated techniques.

Since it emits infrared rays by itself and shoots it using it, gesture recognition is possible because it has less influence of external illumination compared with a work using a general camera.

Basically, Kinect is aware of depth by randomly scattering infrared rays in the form of a number of point light sources, and when it encounters a three-dimensional object, the distribution pattern originally transmitted is distorted according to the shape of the object.

Kinect is skeletonized based on dynamic objects, and Kinect can recognize which gestures the user is expressing by recognizing and skeletonizing the user.

This is accomplished by constructing an optimal scenario that can be used by multiple users through multiple Kinect.

In order to solve the above problems, according to the present invention, it is possible to recognize gestures of a plurality of users rather than a single user by using a plurality of Kinect, which is one of the Depth sensors, instead of one, There is an effect that content can be provided.

Claims (3)

A multi-user recognition algorithm using Kinect, and a seamless gesture recognition SW program that can effectively recognize a gesture of a user in the recognition range.
2. The method of claim 1, wherein the multi-user recognition algorithm
A method for recognizing a plurality of users based on a Multi Kinect based on the method of recognizing a plurality of users
The method according to claim 1, wherein the seamless gesture recognition SW program
Multi-Kinect-based Seamless Gesture Recognition Method which is able to recognize the user's gesture seamlessly at any position by removing the blind spot that can not recognize the user's gesture within the recognition range of the sensor by using the Depth sensor
KR1020150102072A 2015-07-18 2015-07-18 Multi kinect based seamless gesture recognition method KR20170010288A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150102072A KR20170010288A (en) 2015-07-18 2015-07-18 Multi kinect based seamless gesture recognition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150102072A KR20170010288A (en) 2015-07-18 2015-07-18 Multi kinect based seamless gesture recognition method

Publications (1)

Publication Number Publication Date
KR20170010288A true KR20170010288A (en) 2017-01-26

Family

ID=57992912

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150102072A KR20170010288A (en) 2015-07-18 2015-07-18 Multi kinect based seamless gesture recognition method

Country Status (1)

Country Link
KR (1) KR20170010288A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107193384A (en) * 2017-06-29 2017-09-22 云南大学 Based on Kinect coloured images in mouse and the switching method of keyboard emulation behavior
CN107563295A (en) * 2017-08-03 2018-01-09 中国科学院自动化研究所 Comprehensive human body method for tracing and processing equipment based on more Kinect
CN108958490A (en) * 2018-07-24 2018-12-07 Oppo（重庆）智能科技有限公司 Electronic device and its gesture identification method, computer readable storage medium
CN109344701A (en) * 2018-08-23 2019-02-15 武汉嫦娥医学抗衰机器人股份有限公司 A kind of dynamic gesture identification method based on Kinect

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107193384A (en) * 2017-06-29 2017-09-22 云南大学 Based on Kinect coloured images in mouse and the switching method of keyboard emulation behavior
CN107193384B (en) * 2017-06-29 2020-01-10 云南大学 Switching method of mouse and keyboard simulation behaviors based on Kinect color image
CN107563295A (en) * 2017-08-03 2018-01-09 中国科学院自动化研究所 Comprehensive human body method for tracing and processing equipment based on more Kinect
CN107563295B (en) * 2017-08-03 2020-07-28 中国科学院自动化研究所 Multi-Kinect-based all-dimensional human body tracking method and processing equipment
CN108958490A (en) * 2018-07-24 2018-12-07 Oppo（重庆）智能科技有限公司 Electronic device and its gesture identification method, computer readable storage medium
CN109344701A (en) * 2018-08-23 2019-02-15 武汉嫦娥医学抗衰机器人股份有限公司 A kind of dynamic gesture identification method based on Kinect
CN109344701B (en) * 2018-08-23 2021-11-30 武汉嫦娥医学抗衰机器人股份有限公司 Kinect-based dynamic gesture recognition method

Similar Documents

Publication Publication Date Title
IL274429B (en) Methods and systems for displaying stereoscopy with a freeform optical system with addressable focus for virtual and augmented reality
EP4235263A3 (en) Gaze-based user interactions
WO2013006590A3 (en) Dynamic lighting and rendering techniques implemented in gaming environments
WO2014197338A3 (en) Head mounted display based on optical prescription of a user
ZA202200581B (en) Gaming video processing system
EP3066551B8 (en) Multi-modal gesture based interactive system and method using one single sensing system
NZ744400A (en) Eye image collection, selection, and combination
KR20170010288A (en) Multi kinect based seamless gesture recognition method
JP2015515688A5 (en)
AR091355A1 (en) PROCEDURE AND APPLIANCE TO PROVIDE FOCAL CORRECTION OF INFORMATION EXHIBITED
EP3391030A4 (en) Apparatus and method for generating 3-d data for an anatomical target using optical fiber shape sensing
WO2013165646A3 (en) User input processing with eye tracking
WO2014181205A3 (en) Methods and apparatus for controlling lighting based on user manipulation of a mobile computing device
MX352773B (en) Adaptive event recognition.
WO2014151031A3 (en) Visual gestures
WO2016154026A3 (en) Retroreflective light field display
EP3502851A4 (en) In-cell transparent touch control display panel, and manufacturing method and driving method therefor
AU360961S (en) Display screen with graphical user interface
EP3373481A4 (en) Visible light signal generation method, signal generation device and program
GB2498671B (en) Method and apparatus for using gestures to control a laser tracker
WO2014078432A3 (en) Devices, systems, and methods for visual-attribute refinement
MX352442B (en) Method relating to presence granularity with augmented reality.
GB201208523D0 (en) Gesture recognition
EP3188034A4 (en) Display terminal-based data processing method
WO2011071305A3 (en) Optical touch screen

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E601 Decision to refuse application