Motion recognition method based on fuzzy neural network and graph model reasoning

A technology of fuzzy neural network and action recognition, applied in the field of human motion recognition, can solve the problems of low application efficiency of motion capture data, high computing cost, and inability to distinguish between closely matched motion retrievals, etc.

Inactive Publication Date: 2017-09-26
XIAN TECH UNIV
View PDF6 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an action recognition method based on fuzzy neural network and graphical model reasoning, which overcomes the high computational cost of existing methods, low application efficiency of motion capture data and indistinguishable retrieval of closely matched motions Questions in place

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
  • Motion recognition method based on fuzzy neural network and graph model reasoning
  • Motion recognition method based on fuzzy neural network and graph model reasoning
  • Motion recognition method based on fuzzy neural network and graph model reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0083] Related technology in the present invention is introduced as follows:

[0084] (1) Gesture segmentation technology based on the skin color model: skin color is the most obvious and simple feature that distinguishes the face and hands from the surrounding environment, so by determining the accurate skin color area threshold condition, the face and hands area can be located. The image color space of the video is RGB color space, but in the RGB space, the skin color of the human body is greatly affected by the brightness, which makes it difficult to separate the skin color points from the non-skin color points. Skin tones are very different, mainly due to differences in saturation and brightness, while skin tones do not vary much in chroma. In the chromaticity space, the HSV color space uses the three dimensions of hue H, saturation S, a...

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

The invention discloses a human motion recognition method based on fuzzy neural network and graph model reasoning. The method specifically comprises the steps as follows: step 1, a Kinect device is used for shooting monocular and depth videos and a human motion video sequence database is constructed; step 2, each frame of image of the video Vi is extracted and a motion framework is obtained with a human framework extraction method; step 3, corresponding representative frame images constitute a human motion representative frame image database DRF={RFi}; step 4, classification of data is trained on the basis of all obtained motion posture key frame framework characteristics; step 5, a fuzzy nerve network system based on probabilistic graphical model is constructed for motion semantic reasoning to recognize the body posture semantic determined by each representative frame; step 6, motion semantic sequences are classified on the basis of an FNNGM graphical model structure constructed in the step 5. The method solves the problems that existing methods are higher in calculation cost and lower in application efficiency of motion capture data.

Description

technical field [0001] The invention belongs to the technical field of human motion recognition, and in particular relates to an action recognition method based on fuzzy neural network and graphical model reasoning. Background technique [0002] In recent years, human action recognition has become a core problem in the field of computer vision. From simple action recognition under early restricted conditions to complex action recognition in real natural scenes; from single-person action recognition to interactive action and even large-scale group action recognition. Due to the complexity and uncertainty of human motion, action recognition is still a very challenging topic. Many action recognition methods focus on designing effective descriptors or features for classification through feature matching. Previous action recognition mainly consists of two categories: feature representation and action classification. Feature representation is always a key task for action recogn...

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): G06K9/00G06K9/62G06N3/08G06N5/04
CPCG06N5/04G06N3/08G06V40/20G06F18/24137
Inventor 肖秦琨赵一丹高嵩
Owner XIAN TECH 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