Unlock instant, AI-driven research and patent intelligence for your innovation.

A Human Action Recognition Method Based on Supervised Isometric Mapping

A technology of human action recognition and isometric mapping, which is applied in the field of human action recognition of distance mapping, can solve problems such as confusion and recognition difficulty, and achieve the effects of easy implementation, improved classification accuracy, and reduced algorithm complexity.

Inactive Publication Date: 2016-08-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In some existing methods, in order to use as much information as possible to represent actions, a variety of feature fusion methods are used. However, this puts forward higher requirements for computing speed to a certain extent. Difficult to identify, counterproductive to confusion

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
  • A Human Action Recognition Method Based on Supervised Isometric Mapping
  • A Human Action Recognition Method Based on Supervised Isometric Mapping
  • A Human Action Recognition Method Based on Supervised Isometric Mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0046] A human action recognition method based on supervised isometric mapping, comprising the steps of:

[0047] S1. Extract the foreground of the video through the codebook (codebook) method to obtain a binarized human body foreground image;

[0048] S2. Perform morphological processing and normalization on the foreground image of the human body to obtain a silhouette image of the human body;

[0049] S3. Periodic analysis is performed on the human body silhouette image sequence, and for each video, the video is represented by a key frame containing a complete motion cycle;

[0050] S4. Vectorize the key frame of the human silhouette image, and perform feature dimensionality reduction through supervised isometric mapping (S-ISOMAP);

[0051] S5. Recognize the dimensionally reduced features through a nearest neighbor classifier based on Haus...

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 action recognition method based on supervised isometric mapping, which belongs to the field of pattern recognition and computer vision. image; S2, perform morphological processing and normalization on the human foreground image to obtain a human silhouette image; S3, perform periodic analysis on the human silhouette image sequence, and each video is represented by a key frame containing a complete action cycle The video; S4, vectorize the key frames of the human silhouette image, and perform feature dimension reduction through supervised isometric mapping; S5, identify the dimension-reduced features through a nearest neighbor classifier based on Hausdorff distance. The invention breaks through the limitations of the existing algorithms, reduces the complexity of the algorithm while improving the classification accuracy, and makes it easier to implement in practical engineering applications.

Description

technical field [0001] The invention relates to the field of pattern recognition and computer vision, in particular to a human action recognition method based on supervised isometric mapping. Background technique [0002] The purpose of human motion analysis is to recognize and understand human actions, and research based on this is called action recognition. Today, with the rapid development of science and technology, motion recognition is used in many fields such as intelligent monitoring, identity confirmation, motion analysis, human-computer interaction, etc., and has relatively high academic theoretical value and extensive market practical value in these fields. [0003] In recent years, human action recognition has gradually become a very challenging research direction in computer vision, and great progress has been made, but there are still many problems to be solved, and the existing methods are far from meeting the needs of practical applications. There is still a ...

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 Patents(China)
IPC IPC(8): G06K9/64
Inventor 程建刘海军周圣云王峰李鸿升
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA