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

Motion mode identification method and device

A motion pattern and recognition method technology, applied in the field of pattern recognition, can solve the problems of unsatisfactory recognition effect, dimensional disaster, large amount of data, etc.

Inactive Publication Date: 2018-09-11
CHENGDU LEDONG INFORMATION TECH CO LTD
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the method based on computer vision has strict requirements on lighting conditions, and the large amount of data may easily lead to the disaster of dimensionality, so the final recognition effect is not ideal.

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 mode identification method and device
  • Motion mode identification method and device
  • Motion mode identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0134] As an implementation manner, the feature extraction module 220 includes:

[0135] The first extraction unit is used for feature extraction based on the softmax regression classifier to perform feature extraction on the smooth filtered original data to obtain the first motion feature data;

[0136] The second extraction unit is used for feature extraction based on the naive Bayesian classifier to perform feature extraction on the smoothed and filtered original data to obtain second motion feature data;

[0137] The third extraction unit is used to perform feature extraction on the smoothed and filtered original data based on the feature extraction method of the decision tree classifier to obtain the third motion feature data;

[0138] The pattern recognition module 230 includes:

[0139] A first identification unit, configured to identify the first motion feature data to obtain a first motion pattern;

[0140] a second identification unit, configured to identify the se...

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 embodiment of the invention provides a motion mode identification method and device, belonging to the field of mode identification. The method comprises the steps of: obtaining original motion data showing motion modes, performing smoothing filtering of the original motion data, based on different feature extraction modes corresponding to a plurality of classifiers, performing feature extraction of the original motion data after smoothing filtering, obtaining a plurality of motion feature data, performing identification of the motion feature data, obtaining a plurality of motion modes, anddetermining a final motion mode from the motion modes based on a preset rule. The method performs integration of classifiers through different features of the different classifiers and different feature extraction modes to obtain a final motion mode according to the preset rule so as to avoid a condition that a certain classifier is large in identification result deviation on local feature data so as to improve the identification stability and accuracy rate.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to a motion pattern recognition method and device. Background technique [0002] Motion pattern recognition is a very interesting and challenging problem, which is widely used in sports running, fitness, ball games and other fields. The usual implementation is: a method based on computer vision. The vision-based method is to capture the user's actions through the camera, and then use computer vision-related methods to identify different action patterns. [0003] Computer vision-based technology has been widely used in human body target tracking and pattern recognition for a series of actions. This method requires the installation of cameras at monitoring locations to collect visual data, and then preprocesses the raw data, Feature extraction, object detection, target tracking, and finally through pattern recognition of a series of actions, or through the most popular deep learni...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/20G06V10/40G06F18/241
Inventor 申波
Owner CHENGDU LEDONG INFORMATION TECH CO LTD