A research method of human posture and action based on binocular vision

A technology for human body posture and motion research, applied in image data processing, instruments, calculations, etc., can solve problems such as high cost, high light requirements, complex optoelectronic equipment, etc.

Active Publication Date: 2017-01-11
NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The structured light method has high requirements on equipment and external light, and is expensive
The time-of-flight method directly uses the propagation characteristics of light and sound waves, and does not require the acquisition and analysis of grayscale images, so the acquisition of distance is not affected by the surface properties of objects, but it requires more complex optoelectronic equipment, which is expensive and has a measurement accuracy comparable to that of The sensitivity of the device has a lot to do with

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 research method of human posture and action based on binocular vision
  • A research method of human posture and action based on binocular vision
  • A research method of human posture and action based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0089] The first embodiment of the present invention is used to determine whether the subject squatting and translation in the left-right direction and the front-rear direction is realized by the following steps:

[0090] S1: Place the left camera and the right camera on the same horizontal line parallel to the ground, where the two cameras are of the same model, the distance between the two cameras is a set value, and both cameras can shoot a complete upper body of the human body,

[0091] Among them, the two cameras are MV-VS078FC cameras, and the two cameras are fixed at the same level by tripods;

[0092] S2: Perform dual-target calibration on the left camera and the right camera. First, prepare a rectangular calibration plate with multiple circular feature points, wherein the multiple circular feature points are arranged in an array of multiple rows and columns, which are located in the same row. The centers of the circular feature points are on the same line, and the ce...

no. 2 example

[0142] The second embodiment of the present invention is used to judge the arm posture of the collected person. Specifically, it can judge the open angle of the collected person's arms and the degree of bending of the arms respectively. Steps S1 to S29 are the same as the first embodiment. , so do not repeat, assuming that the multiple skin color regions in S12 also include the left hand and right hand of the person being collected, and the centroid points of the left hand and right hand of the person being collected are not discarded in S30, and the arm posture of the person being collected is judged by the following steps:

[0143] The subject keeps his arms straight, so that the arms are in the same plane and the plane where the arms are located forms an included angle of 90 degrees with the vertical plane. Use the above steps S10 to S28 to calculate the subject's face, left hand and right hand respectively. The coordinates of the centroid point in the world coordinate syste...

no. 3 example

[0151] The third embodiment of the present invention is used for judging whether the collected person has moved rapidly within a period of time. The steps S1 to S30 are the same as the first embodiment, so they will not be repeated. The following steps are used to judge whether the collected person has moved within a period of time. Did fast movement occur:

[0152] Set a speed threshold V T ;

[0153] Calculate the moving distance d of the centroid point of the face in the time t0 ~ t1,

[0154]

[0155] Since the sudden change of human motion state is often completed in a very short time, the time interval between t0 and t1 should not be too large. Determine the number of image frames that differ between t0 and t1), that is, assuming that the frame rates of the video captured by the left camera and the right camera are both f, then t1-t0=5 / f;

[0156] Calculate the average velocity of the face centroid in the time t0 ~ t1:

[0157] v=d / (t1-t0);

[0158] when v>V T ,...

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 binocular vision-based human body posture and action research method. Firstly, internal and external parameters of a camera are acquired through binocular calibration, coordinates of a centroid point of each skin color area are extracted from an image shot by the camera, and the centroid point is matched and judged. Then, coordinates of the matched centroid point in a world coordinate system are found with the world coordinate system as a datum. Finally, the gesture and the action of the human body are judged according to the coordinates of the centroid point in the world coordinate system. According to the binocular vision-based human body posture and action research method, a large number of images do not need to be shot, centroid points of human body key parts such as the face and two hands can be matched in a three-dimensional mode through acquiring video frames in real time, the position relationship among the human body key parts is acquired, and the running cost is low.

Description

technical field [0001] The present invention relates to a method for researching human posture and movement, in particular to a method for researching human posture and movement based on binocular vision. Background technique [0002] With the development of computer technology, people can use computers to complete many difficult tasks. The technology of accurately recognizing human actions by computer can be widely used in the fields of intelligent human-computer interaction, virtual reality, video surveillance and digital entertainment, and is currently a research hotspot in the field of computer vision and pattern recognition. In some virtual reality fields, such as digital entertainment, computers are usually required to transmit stimulation signals to human senses on the one hand, and receive the operator's response, such as changes in body posture, on the other hand, and then according to the position of the human body itself and state transitions to adjust the stimul...

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): G06T7/00G06T7/60
Inventor 叶青董俊峰张永梅
Owner NORTH CHINA UNIVERSITY OF TECHNOLOGY
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