Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Human movement recognition method based on multistage characteristics

A technology of human motion recognition and motion recognition, applied in character and pattern recognition, instruments, computer components, etc., to achieve effective representation and improve accuracy

Active Publication Date: 2014-09-03
TIANJIN UNIV
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, human action recognition is still a challenging task due to the interference of factors such as the diversity of human shapes, illumination changes, and occlusions.

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
  • Human movement recognition method based on multistage characteristics
  • Human movement recognition method based on multistage characteristics
  • Human movement recognition method based on multistage characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0024] In order to improve the accuracy of action recognition, an embodiment of the present invention provides a human action recognition method based on multi-level features, see figure 1 , see the description below:

[0025] 101: Extracting spatio-temporal interest points of each frame image in the original video;

[0026] For a given arbitrary human action dataset, it can be divided into a training set and a test set. Without loss of generality, the examples of the present invention use Laptev [1] The spatio-temporal interest point method proposed by et al. to extract features. Spatio-temporal interest points are responses to events occurring at specific times and locations in image sequences distributed along time. Laptev extends the two-dimensional local interest point ...

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 movement recognition method based on multistage characteristics. The human movement recognition method based on the multistage characteristics includes the steps of extracting a space-time interesting point of each frame of image in an original video, classifying the obtained space-time interesting points according to the positions of the human skeletons, obtaining human areas, establishing multiple stages according to the obtained human areas, clustering the space-time interesting points included in the human areas in the stages in a training set according to a clustering algorithm, obtaining corresponding dictionaries, extracting word bag characteristics of the human areas in the training set and a test set through a word bag model, fusing the word bag characteristics of the obtained three stages, and learning and judging the human movement through a hidden conditional random field model for movement recognition. By means of the method, local characteristics can be represented more effectively, and tests verify that the method improves the accuracy of movement recognition.

Description

technical field [0001] The invention relates to the fields of computer vision and human action recognition, in particular to a multi-level feature-based human action recognition method. Background technique [0002] Human action recognition is a very important research topic in the field of computer vision and machine learning, because it has a wide range of applications in intelligent video surveillance, human-computer interaction and other fields. In recent years, with the popularity of multi-view cameras and depth cameras, the use of multi-modal information for human action recognition has become more and more popular. However, human action recognition is still a challenging task due to the interference of factors such as diversity of human body shapes, illumination changes, and occlusions. [0003] Traditional action recognition methods use the features of the whole human body to obtain global information. However, in some cases, multi-level features can represent local...

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
IPC IPC(8): G06K9/00G06K9/62
Inventor 苏育挺刘安安马莉
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com