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

A method and device for extracting human body features in image processing

A technology for human body feature and image processing, applied in the field of image processing, can solve the problem of low extraction accuracy, and achieve the effects of simple method, improved accuracy, and satisfying processing speed requirements.

Active Publication Date: 2019-06-18
SUMAVISION TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method and device for extracting human body features in image processing, so as to overcome the problem of low accuracy in extracting the center points of human body parts in the related art

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 method and device for extracting human body features in image processing
  • A method and device for extracting human body features in image processing
  • A method and device for extracting human body features in image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] like figure 1 Shown is an exemplary flowchart of a method for extracting human body features in image processing provided by an embodiment of the present invention. The method includes the following steps:

[0038] Step 101: For a pre-acquired human body image, calculate the probability that each pixel in the human body image belongs to each human body part.

[0039] Step 102: For any human body part whose central point is to be extracted, the basic point set of the human body part is composed of points whose probability of belonging to the human body part is greater than a first preset threshold.

[0040] Step 103: Obtain points with probabilities greater than a second preset threshold from the basic point set to form a growing point set, wherein the second preset threshold is greater than the first preset threshold.

[0041] Step 104: For any point in the set of growing points, when the point satisfies the preset condition, perform the following operations: use the p...

Embodiment 2

[0065] like image 3 As shown, taking the extraction of the center point of the head as an example, the method for extracting human body features in image processing provided in the embodiment of the present invention is described, and the method includes the following steps:

[0066] Step 301: In the pre-acquired human body image, obtain points whose probability of belonging to the head is not 0, and form an initial point set of the head.

[0067] Step 302: Filter out points in the initial point set whose probability is less than or equal to the first preset threshold, and filter out points that are not adjacent to other points on the head to form a basic point set.

[0068] Step 303: Obtain points with probability greater than a second preset threshold from the basic point set to form a growing point set.

[0069] Step 304: For any point in the set of growing points, when the point satisfies the preset condition, perform the following operations: take the point as the seed ...

Embodiment 3

[0075] Based on the same inventive concept, the embodiment of the present invention also provides a device for extracting human body features in image processing, such as Figure 4 As shown, the device includes:

[0076] A probability calculation module 401, configured to calculate the probability that each pixel in the human body image belongs to each human body part for the pre-acquired human body image;

[0077] The basic point set acquisition module 402 is configured to form the basic point set of the human body part from points whose probability of belonging to the human body part is greater than a first preset threshold for any human body part whose central point is to be extracted;

[0078] A growing point set determination module 403, configured to acquire points with a probability greater than a second preset threshold from the basic point set to form a growing point set, wherein the second preset threshold is greater than the first preset threshold;

[0079] The see...

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 relates to a human body characteristic extraction method and apparatus in image processing. The method comprises the following steps: in a human body image, for a human body part, of which a center point is to be extracted, concentration starts from basic points of the human body part and a set of growing points is selected; for any point of the growing point set, when the point satisfies the preset condition, a seed area of a seed point is determined with the point as the seed point; for each seed area, the gravity center of the seed area is calculated; for each gravity center, the predicted probability that the gravity center is the center point of the human body part is calculated; and according to the predicted probability of each gravity center obtained through calculating, the center point of the human body part is determined. The method provided by the invention can improve the accuracy of the center point extraction and satisfy the speed demand of the real-time processing of an image extracting center.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for extracting human body features in image processing. Background technique [0002] Somatosensory technology is not only used in the field of games, but also in fields such as security, health care, entertainment and shopping. In short, the development of somatosensory technology has brought revolutionary changes to the way of human-computer interaction. [0003] Somatosensory technology controls the somatosensory device by recognizing the motion characteristics of the human body, and in the process of recognizing the motion characteristics, it is necessary to extract the center points of various parts of the human body. For example, in optical sensing, it is first necessary to identify the human body, and then divide the various parts of the human body (such as the head, torso, elbow, hand, etc.), and then extract the central point from each part as the rec...

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): G06K9/00G06T7/66
Inventor 余大勇马昆
Owner SUMAVISION TECH CO LTD