A 3D gesture recognition method
A gesture recognition and gesture technology, applied in the field of 3D gesture recognition, can solve the problems of complex calculation, high computer configuration requirements, unfavorable wide application, etc., and achieve the effect of low complexity, simple algorithm and high accuracy rate.
Active Publication Date: 2017-02-08
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a 3D gesture recognition method to solve the problems in the prior art that the calculation of the computer is too complicated when recognizing human hands, and the required computer configuration requirements are too high, which is not conducive to wide application
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0021] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0022] An embodiment of a 3D gesture recognition method of the present invention: a 3D gesture recognition method, comprising the following steps:
[0023] Step 1, through the first layer classifier, segment the trajectory of the gestures to obtain the stroke trajectories that make up the gestures;
[0024] Step 2, converting the stroke track into a corresponding standard stroke number through a standardization process;
[0025] Step 3, extracting the stroke numbers and stroke lengths of multiple actions of the gesture to form a feature sequence of the gesture;
[0026] Step 4, the feature sequen...
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
Login to View More Abstract
The present invention relates to the fields of computer vision and human-computer interaction, and specifically relates to a 3D gesture recognition method, comprising the following steps: segmenting the trajectory of the gesture through a first-layer classifier to obtain the stroke trajectories that compose each gesture; The standardization process transforms the stroke trajectory into the corresponding standard stroke number; extracts the stroke number and stroke length of multiple actions of the gesture and combines them into a gesture feature sequence; the feature sequence calculates the similarity between the second layer classifier and the template to get the class to which the gesture belongs . This method recognizes and standardizes the changing features in each layer, uses multi-layer recognition and multi-layer standardization, and finally obtains the recognition result, which can accurately calculate the similarity of the stroke direction feature and the similarity of the motion feature sequence . The algorithm is simple, the complexity is low, and the correct rate is high.
Description
technical field [0001] The invention relates to the fields of computer vision and human-computer interaction, in particular to a 3D gesture recognition method. Background technique [0002] The interaction between human and computer has increasingly become an important part of people's daily life, and has gradually become an important research topic in the computer field. In gesture recognition, the most basic and key is the recognition of gestures. After obtaining the trajectory of the dynamic gesture, the computer can extract its features and identify it according to the feature information. This algorithm proposes a new multi-layer classification algorithm based on stroke features and DTLS. First, the motion trajectory is divided into multiple strokes, and the stroke features are standardized. Then, the DTLS similarity is used for matching and recognition to obtain the class to which the gesture belongs. [0003] The invention patent application with the Chinese patent ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/66
Inventor 程洪罗军杨路
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA