Pose recognition method of leaner

A recognition method and learner's technology, applied in character and pattern recognition, biological models, instruments, etc., can solve problems such as incomplete information extraction and information redundancy.

Active Publication Date: 2017-11-03
SHAANXI NORMAL UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above pose recognition model uses depth image or image difference method to extract the human target in the target extraction stage; in the feature extraction stage, the Hu moment is extracted as the feature vector, and the Hu moment cannot completely extract the information in the image, and they are non-normal handed over, with information redundancy

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
  • Pose recognition method of leaner
  • Pose recognition method of leaner
  • Pose recognition method of leaner

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] Taking the postures of the learner raising his hand, sitting upright, and bowing his head as examples, the steps of the learner posture recognition method are as follows:

[0093] (1) Separation of portrait and background

[0094] The bee colony algorithm that introduces Levi's flight and dynamic weights optimizes the normalized cut, segments the learner's pose image, obtains the binary image of the original image, and realizes the separation of the portrait from the background. The steps are as follows:

[0095] 1) Perform fuzzy C-means clustering preprocessing on the red, green, and blue color channels of the color image respectively, and divide the image into n blocks of maximum similarity areas. In this embodiment, n is 14, and each area is selected on the three color channels The average value of the gray value represents the pixel value of this area, and the undirected weighted graph G=(V, E) is constructed with the pixel values ​​of all areas, V is a vertex in th...

Embodiment 2

[0161] Taking the postures of the learner raising his hand, sitting upright, and bowing his head as examples, the steps of the learner posture recognition method are as follows:

[0162] (1) Separation of portrait and background

[0163] The bee colony algorithm that introduces Levi's flight and dynamic weights optimizes the normalized cut, segments the learner's pose image, obtains the binary image of the original image, and realizes the separation of the portrait from the background. The steps are as follows:

[0164] 1) Perform fuzzy C-means clustering preprocessing on the three color channels of red, green, and blue respectively, divide the image into n blocks of maximum similarity areas, n is 6, and take the gray value of each area on the three color channels The average value of represents the pixel value of this area, and the undirected weighted graph G=(V,E) is constructed with the pixel values ​​of all areas, V is a vertex in the graph, and E is an edge connecting two...

Embodiment 3

[0193] Taking the postures of the learner raising his hand, sitting upright, and bowing his head as examples, the steps of the learner posture recognition method are as follows:

[0194] (2) Separation of portrait and background

[0195] The bee colony algorithm that introduces Levi's flight and dynamic weights optimizes the normalized cut, segments the learner's pose image, obtains the binary image of the original image, and realizes the separation of the portrait from the background. The steps are as follows:

[0196] 1) Perform fuzzy C-means clustering preprocessing on the red, green, and blue color channels of the color image respectively, divide the image into n blocks of maximum similarity areas, n is 20, and take the gray value of each area on the three color channels The average value of represents the pixel value of this area, and the undirected weighted graph G=(V,E) is constructed with the pixel values ​​of all areas, V is a vertex in the graph, and E is an edge con...

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 is a pose recognition method of a leaner. The method comprises steps of separation of a portrait and a background; using mathematical morphological operation to extract a profile image of a learner for a binary image; using a Zernike matrix to carry out feature extraction; adopting a support vector machine to train the feature vectors; and recognizing poses of the learner. According to the invention, by introducing the Levy flight mechanism in a bee colony algorithm, according to different flight step lengths, different searching modes are adopted, so the variety of the population can be enriched; premature convergence and falling into the local optimum can be avoided; a dynamic weighting mechanism is adopted in the bee colony algorithm, and an individual bee searching mode is adjusted according to the evolutionary rate of the population, so global searching and local searching ability are dynamically balanced; and the method is advantaged by good segmentation effects and high recognition rate, and can be used for recognition of poses of the learners and recognition and classification of other images.

Description

technical field [0001] The invention relates to the technical fields of image processing and machine vision, in particular to a learner gesture recognition method based on bee colony algorithm optimized normalized cut. Background technique [0002] With the development of network technology and the advent of the digital age, online learning, as a convenient and novel way of learning, has become a dominant form of distance education, which is increasingly affecting our study and work. The learner's body posture partly reflects the learner's learning state. Learner gesture recognition can effectively evaluate the learning status of learners in the online learning process, so that teachers can get more feedback information, and it plays an important role in analyzing the learning status of learners and improving the teaching process. [0003] Zhang Hongyu and others proposed a multi-learner pose recognition method based on depth images. Firstly, the infrared sensor of Kinect i...

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 Applications(China)
IPC IPC(8): G06K9/62G06N3/00
CPCG06N3/006G06F18/2411G06F18/214
Inventor 郭敏邝毓茜马苗陈昱莅郭宗华
Owner SHAANXI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap