CN105045390A - Human upper limb skeleton gesture identification method - Google Patents
Human upper limb skeleton gesture identification method Download PDFInfo
- Publication number
- CN105045390A CN105045390A CN201510395076.3A CN201510395076A CN105045390A CN 105045390 A CN105045390 A CN 105045390A CN 201510395076 A CN201510395076 A CN 201510395076A CN 105045390 A CN105045390 A CN 105045390A
- Authority
- CN
- China
- Prior art keywords
- human
- coordinate data
- data
- upper limb
- human body
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
A human upper limb skeleton gesture identification method relates to the technical field of man-machine interaction. The identification method comprises: with the adoption of a single-camera structure, obtaining positions of palm, arm, shoulder and head regions of a human body in each frame of image by utilizing a skin color model of the human body in combination with a background subtraction method based on a Gaussian model and the like; performing difference operation on a background image and a current image, and detecting a foreground region; updating the established background image with a double-background updating method; acquiring joint points of human upper limb, establishing a coordinate system of the joint points of the human body, and defining original coordinate data of each joint point; storing the original coordinate data of each joint point in a data set; and acquiring current coordinate data of each joint point and storing the coordinate data of each joint point in the data set. According to the method, obtained three-dimensional information of human skeleton is analyzed to form a series of spatial gestures, so that a computer can identify various gestures of people.
Description
Technical field:
The present invention relates to human-computer interaction technique field, be specifically related to a kind of human upper limb bone gesture identification method.
Background technology:
Along with the development of computer technology, operational order also gets more and more, and function is also more and more stronger.Along with pattern-recognition, as the development of the input equipment such as speech recognition, Chinese Character Recognition, operator and computing machine become possibility alternately being similar in natural language or this one-level of restricted natural language.In addition, carry out man-machine interaction by figure also to attract people and go to study.These man-machine interactions can be described as intelligentized man-machine interaction.The research work of this respect is actively developed.
Man-machine interaction, human-computer interaction (English: Human – ComputerInteraction or Human – MachineInteraction, to be called for short HCI or HMI) are the knowledge of an interactive relation between Study system and user.System can be various machine, also can be computerized system and software.Human-computer interaction interface typically refers to the visible part of user.User is exchanged with system by human-computer interaction interface, line operate of going forward side by side.The broadcasting button of little Source Music, greatly to the instrument panel on aircraft or the pulpit of generating plant.The design of human-computer interaction interface will comprise the understanding (i.e. mental model) of user to system, and that is availability in order to system or user friendly.
Along with the development of human-computer interaction technology, body sense equipment obtains use in many occasions and field gradually as the input equipment of a kind of replacement or supplementary common keyboard and mouse.Body sense interaction technique makes people become possibility alternately by equipment such as various action and computing machines, and operator can coordinate display to realize the interactive function with the equipment such as computing machine by making specific gesture path on body propagated sensation sensor.Microsoft Kinect is one of popular at present body sense video camera.The data that Kinect is got by the analysis of body sense camera are also analyzed, and the three-dimensional data finally returning 20 articulation points tracked generates a width shell system, and this cover system only comprises the three-dimensional information of each articulation point of human body, can not carry out gesture identification.
Summary of the invention:
The object of this invention is to provide a kind of human upper limb bone gesture identification method, it is by analyzing the skeleton three-dimensional information obtained, make it to become a series of body sense gesture, calculating function is identified the various gestures that people makes, make discrimination by distance, the colour of skin, block, illumination, the factor such as motion impact, applied environment complicated and changeable can be adapted to.
In order to solve the problem existing for background technology, the present invention is by the following technical solutions: its recognition methods is: step one, adopt single camera structure under, utilize the complexion model of the human body background subtraction method etc. combined based on Gauss model to obtain the position of the palm of human body in every two field picture, arm, shoulder and head zone;
Step 2, utilize background image and present image to make difference, detect foreground area;
Step 3, the two background update methods of utilization upgrade the background image set up;
The articulation point of step 4, collection human upper limb, sets up human joint points coordinate system, defines the original coordinates data of each articulation point;
Step 5, by each articulation point original coordinates data stored in data group;
Step 6, gather each current body joint point coordinate data, and by the coordinate data of each articulation point stored in data group;
Step 7, these body joint point coordinate data are utilized to set up human hands 3D model; Utilize the direction of motion of hand region in human body sequence of video images, hand shape, later location parameter correction 3D model;
Step 8, the original coordinates data of the coordinate data of each articulation point current and corresponding joint point to be contrasted, gesture is judged and identifies;
Step 9, finally HMM is utilized to identify various hand motion and use experimental verification recognition result.
The present invention is by analyzing the skeleton three-dimensional information obtained, make it to become a series of body sense gesture, calculating function is identified the various gestures that people makes, make discrimination by distance, the colour of skin, block, illumination, the factor such as motion impact, applied environment complicated and changeable can be adapted to.
Embodiment:
This embodiment is by the following technical solutions: its recognition methods is: step one, adopt single camera structure under, utilize the complexion model of the human body background subtraction method etc. combined based on Gauss model to obtain the position of the palm of human body in every two field picture, arm, shoulder and head zone;
Step 2, utilize background image and present image to make difference, detect foreground area;
Step 3, the two background update methods of utilization upgrade the background image set up;
The articulation point of step 4, collection human upper limb, sets up human joint points coordinate system, defines the original coordinates data of each articulation point;
Step 5, by each articulation point original coordinates data stored in data group;
Step 6, gather each current body joint point coordinate data, and by the coordinate data of each articulation point stored in data group;
Step 7, these body joint point coordinate data are utilized to set up human hands 3D model; Utilize the direction of motion of hand region in human body sequence of video images, hand shape, later location parameter correction 3D model;
Step 8, the original coordinates data of the coordinate data of each articulation point current and corresponding joint point to be contrasted, gesture is judged and identifies;
Step 9, finally HMM is utilized to identify various hand motion and use experimental verification recognition result.
This embodiment is by analyzing the skeleton three-dimensional information obtained, make it to become a series of body sense gesture, calculating function is identified the various gestures that people makes, make discrimination by distance, the colour of skin, block, illumination, the factor such as motion impact, applied environment complicated and changeable can be adapted to.
Claims (1)
1. a human upper limb bone gesture identification method, it is characterized in that its recognition methods is: step one, adopt single camera structure under, utilize the complexion model of the human body background subtraction method etc. combined based on Gauss model to obtain the position of the palm of human body in every two field picture, arm, shoulder and head zone;
Step 2, utilize background image and present image to make difference, detect foreground area;
Step 3, the two background update methods of utilization upgrade the background image set up;
The articulation point of step 4, collection human upper limb, sets up human joint points coordinate system, defines the original coordinates data of each articulation point;
Step 5, by each articulation point original coordinates data stored in data group;
Step 6, gather each current body joint point coordinate data, and by the coordinate data of each articulation point stored in data group;
Step 7, these body joint point coordinate data are utilized to set up human hands 3D model; Utilize the direction of motion of hand region in human body sequence of video images, hand shape, later location parameter correction 3D model;
Step 8, the original coordinates data of the coordinate data of each articulation point current and corresponding joint point to be contrasted, gesture is judged and identifies;
Step 9, finally HMM is utilized to identify various hand motion and use experimental verification recognition result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510395076.3A CN105045390A (en) | 2015-07-08 | 2015-07-08 | Human upper limb skeleton gesture identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510395076.3A CN105045390A (en) | 2015-07-08 | 2015-07-08 | Human upper limb skeleton gesture identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105045390A true CN105045390A (en) | 2015-11-11 |
Family
ID=54451982
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510395076.3A Pending CN105045390A (en) | 2015-07-08 | 2015-07-08 | Human upper limb skeleton gesture identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105045390A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110032957A (en) * | 2019-03-27 | 2019-07-19 | 长春理工大学 | A kind of gesture space domain matching process based on bone nodal information |
CN110427100A (en) * | 2019-07-03 | 2019-11-08 | 武汉子序科技股份有限公司 | A kind of movement posture capture system based on depth camera |
CN114463850A (en) * | 2022-02-08 | 2022-05-10 | 南京科源视觉技术有限公司 | Human body action recognition system suitable for multiple application scenes |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104460967A (en) * | 2013-11-25 | 2015-03-25 | 安徽寰智信息科技股份有限公司 | Recognition method of upper limb bone gestures of human body |
CN104615366A (en) * | 2014-12-31 | 2015-05-13 | 中国人民解放军国防科学技术大学 | Gesture interactive method oriented to multiple devices |
CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
CN104636725A (en) * | 2015-02-04 | 2015-05-20 | 华中科技大学 | Gesture recognition method based on depth image and gesture recognition system based on depth images |
-
2015
- 2015-07-08 CN CN201510395076.3A patent/CN105045390A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104460967A (en) * | 2013-11-25 | 2015-03-25 | 安徽寰智信息科技股份有限公司 | Recognition method of upper limb bone gestures of human body |
CN104615366A (en) * | 2014-12-31 | 2015-05-13 | 中国人民解放军国防科学技术大学 | Gesture interactive method oriented to multiple devices |
CN104615244A (en) * | 2015-01-23 | 2015-05-13 | 深圳大学 | Automatic gesture recognizing method and system |
CN104636725A (en) * | 2015-02-04 | 2015-05-20 | 华中科技大学 | Gesture recognition method based on depth image and gesture recognition system based on depth images |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110032957A (en) * | 2019-03-27 | 2019-07-19 | 长春理工大学 | A kind of gesture space domain matching process based on bone nodal information |
CN110032957B (en) * | 2019-03-27 | 2023-10-17 | 长春理工大学 | Gesture spatial domain matching method based on skeleton node information |
CN110427100A (en) * | 2019-07-03 | 2019-11-08 | 武汉子序科技股份有限公司 | A kind of movement posture capture system based on depth camera |
CN114463850A (en) * | 2022-02-08 | 2022-05-10 | 南京科源视觉技术有限公司 | Human body action recognition system suitable for multiple application scenes |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104460967A (en) | Recognition method of upper limb bone gestures of human body | |
US10394334B2 (en) | Gesture-based control system | |
US20150084859A1 (en) | System and Method for Recognition and Response to Gesture Based Input | |
CN103809733B (en) | Man-machine interactive system and method | |
Rautaray et al. | Real time multiple hand gesture recognition system for human computer interaction | |
Banerjee et al. | Mouse control using a web camera based on colour detection | |
CN107450714A (en) | Man-machine interaction support test system based on augmented reality and image recognition | |
CN109145802B (en) | Kinect-based multi-person gesture man-machine interaction method and device | |
US20130038521A1 (en) | Systems and methods of camera-based fingertip tracking | |
CN106598227A (en) | Hand gesture identification method based on Leap Motion and Kinect | |
CN101807114A (en) | Natural interactive method based on three-dimensional gestures | |
KR102147430B1 (en) | virtual multi-touch interaction apparatus and method | |
KR20110070331A (en) | Apparatus for user interface based on wearable computing environment and method thereof | |
US20160086349A1 (en) | Tracking hand pose using forearm-hand model | |
CN105045390A (en) | Human upper limb skeleton gesture identification method | |
JP2016167268A (en) | Gesture modeling device, gesture modeling method, program for gesture modeling system, and gesture modeling system | |
KR101426378B1 (en) | System and Method for Processing Presentation Event Using Depth Information | |
Zhang et al. | A hybrid 2D–3D tangible interface combining a smartphone and controller for virtual reality | |
KR20160141023A (en) | The method of dynamic and static gesture recognition using depth camera and interface of immersive media contents | |
Abdallah et al. | An overview of gesture recognition | |
KR101525011B1 (en) | tangible virtual reality display control device based on NUI, and method thereof | |
Raj et al. | Human computer interaction using virtual user computer interaction system | |
KR101519589B1 (en) | Electronic learning apparatus and method for controlling contents by hand avatar | |
Gupta et al. | Hand gesture based region marking for tele-support using wearables | |
Raees et al. | Thumb inclination-based manipulation and exploration, a machine learning based interaction technique for virtual environments |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151111 |
|
WD01 | Invention patent application deemed withdrawn after publication |