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

A method and device for detect the orientation of a human body in a picture

A technology of human body in pictures, applied in the field of image processing, can solve problems such as the inability to recognize the orientation of human body

Inactive Publication Date: 2018-12-18
北京君正集成电路股份有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method and device for detecting the orientation of a human body in a picture, so as to solve the problem that the orientation of a human body in an image cannot be recognized at present

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 detect the orientation of a human body in a picture
  • A method and device for detect the orientation of a human body in a picture
  • A method and device for detect the orientation of a human body in a picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Embodiments of the present invention provide a method and device for detecting the orientation of a human body in a picture, which solves the problem that the prior art cannot accurately identify the orientation of a human body in a picture.

[0045] see figure 1 A method for detecting the orientation of a human body in a picture provided by an embodiment of the present invention includes:

[0046] S101. Load the image to be detected;

[0047] S102. Use the human body frontal orientation detection model, the human body left orientation detection model, and the human body right orientation detection model to detect the pictures respectively, and detect the frontal orientation to the human body, the left orientation to the human body, and the right orientation to the human body; wherein, will be detected at the same time A human body that is front-facing and left-facing is determined as a left-facing human body, and a human body that is simultaneously detected as front-f...

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 method and device for detecting the orientation of a human body in a picture, which are used for solving the problem that the human body orientation in an image cannot be recognized at present. The method comprises the following steps of: loading a picture to be detected; adopting a human body frontal orientation detection model, a human body left orientation detection model and a human body right orientation detection model to detect the picture, and detecting the frontal orientation human body, the left orientation human body and the right orientation human body, wherein, a human body which is simultaneously detected as frontal orientation and left orientation is determined as left orientation, and a human body which is simultaneously detected as frontal orientation and right orientation is determined as right orientation; outputting the human body orientation detection results.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for detecting the orientation of a human body in a picture. Background technique [0002] With the application of machine learning technology in the field of image processing technology, the application effect of image processing technology has been greatly improved. An important content of image processing technology is content humanoid feature recognition. By using a large amount of data to train the model, it can achieve a high recognition effect on the input image. [0003] However, the currently disclosed human figure detection algorithm adopts a single human figure detection model, which can only detect the human figure in the image, but cannot recognize the orientation of the human body in the image. Generally speaking, the human body detected in the image is facing us or facing away from us, which is called frontal orientation, rotating to th...

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
CPCG06V40/103
Inventor 余慧
Owner 北京君正集成电路股份有限公司