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

Human behavior similarity calculation method and device

A similarity calculation and similarity technology, applied in computing, computer parts, instruments, etc., can solve the problems of low precision, not wide, easily affected by light and shadow coverage, etc., and achieve the effect of simplifying complexity

Active Publication Date: 2019-08-23
SHANGHAI NORMAL UNIVERSITY
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to develop a data processing method aimed at the problems in the prior art, such as low accuracy in human body behavior recognition, easy to be affected by light and shadow, and limited coverage. A Human Behavior Similarity Calculation Method Combining Curve Fitting and Dynamic Time Warping with Wide Coverage and High Accuracy

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 behavior similarity calculation method and device
  • Human behavior similarity calculation method and device
  • Human behavior similarity calculation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] An embodiment of the disclosure of the present invention provides a human behavior similarity calculation method, including the following steps:

[0061] Step 100, obtaining human skeleton depth data, behavior to be tested and template behavior;

[0062] Step 200, converting the obtained human skeleton depth data into spatial three-dimensional coordinate data;

[0063] Step 300, according to the spatial three-dimensional coordinate data, perform dynamic time warping on the behavior to be tested and the behavior of the template to obtain the optimal path;

[0064] Step 400, using curve fitting to correct the optimal path;

[0065] Step 500, according to the corrected optimal path, calculate the similarity between the behavior to be tested and the behavior of the template.

[0066] Wherein, in step 100, obtaining the depth data of the human body skeleton is specifically,

[0067] Step 101, establish a shooting space, and use the Kinect somatosensory device to shoot;

...

Embodiment 2

[0205] The disclosure of the present invention provides a human behavior similarity calculation device, including:

[0206] The obtaining module is used to obtain the depth data of the human skeleton, the behavior to be tested and the template behavior;

[0207] A conversion module, configured to convert the obtained human skeleton depth data into spatial three-dimensional coordinate data;

[0208] The adjustment module is used to perform dynamic time warping on the behavior to be tested and the behavior of the template according to the spatial three-dimensional coordinate data to obtain the optimal path;

[0209] A correction module is used to correct the optimal path by curve fitting;

[0210] The calculation module is used to calculate the similarity between the behavior to be tested and the behavior of the template according to the corrected optimal path.

[0211] Further, the acquisition module includes:

[0212] The shooting unit is used to establish the shooting spac...

Embodiment 3

[0223] Embodiment 5 of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, any one of the methods above is implemented.

[0224]The computer device in this embodiment includes: a processor, a memory, and a computer program stored in the memory and operable on the processor, such as a resource allocation program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the human behavior similarity calculation method are realized. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above device embodiments are implemented.

[0225] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The o...

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 behavior similarity calculation method and device, and the method comprises the following steps: obtaining human skeleton depth data, a to-be-tested behavior, and a template behavior; converting the acquired human skeleton depth data into spatial three-dimensional coordinate data; performing dynamic time warping on the behavior to be tested and the template behavioraccording to the spatial three-dimensional coordinate data to obtain an optimal path; correcting the optimal path by using curve fitting; and calculating the similarity between the behavior to be tested and the template behavior according to the corrected optimal path. The human body behavior similarity calculation method disclosed by the invention is wide in data processing coverage and high inaccuracy, and combines the curve fitting and dynamic time warping.

Description

technical field [0001] The invention relates to the fields of image processing, human body gesture recognition, etc., and in particular to a method and device for calculating similarity of human body behavior. Background technique [0002] Human behavior recognition is to automatically analyze and recognize behaviors from unknown information. It is one of the popular research directions of computer vision. This research field includes many disciplines: signal processing, pattern recognition, machine learning, neurophysiology, psychology, etc. The research results are widely used in human-computer interaction, intelligent video surveillance, virtual reality, sports behavior analysis, eye tracking, etc. [0003] The research goal of human behavior recognition is to make computer vision approach or even achieve the recognition function of human eyes. Because the human eye can obtain effective information in extremely complex scenes, even if a simple action occurs, the human ey...

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): G06K9/00
CPCG06V40/23G06V40/103
Inventor 马燕李盛楠黄慧李顺宝张玉萍
Owner SHANGHAI NORMAL UNIVERSITY