Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image processing method and device, image equipment and storage medium

An image processing and image acquisition technology, applied in the information field, can solve problems affecting video effects, information security issues, etc.

Pending Publication Date: 2020-07-28
BEIJING SENSETIME TECH DEV CO LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When conducting online lectures or webcasting, the user's face or body is completely exposed on the network, which may involve user privacy issues on the one hand, and information security issues on the other.
In order to solve this privacy or security problem, the face image may be covered by mosaics, etc., but this will affect the video effect

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
  • Image processing method and device, image equipment and storage medium
  • Image processing method and device, image equipment and storage medium
  • Image processing method and device, image equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0251] This example provides an image processing method, including:

[0252] Acquire images, the images include objects, including but not limited to human bodies;

[0253] Detect the face node of the human body; the face node can be the contour node of the human face surface;

[0254] Detect the torso node and / or limb node of the human body, where the torso node and / or limb node can be 3D nodes, represented by 3D coordinates; the 3D can include 2D coordinates detected from a 2D image, and then use 2D 2D coordinates obtained by a conversion algorithm from coordinates to 3D coordinates; the 3D coordinates may also be 3D coordinates extracted from 3D images collected by a 3D camera. The limb nodes here can include: upper limb nodes and / or lower limb nodes; nodes, fingertip nodes; the positions of these nodes reflect the movement of the hand and fingers.

[0255] According to the face node, generate the mesh information of the face;

[0256] converting the quaternion accordin...

example 2

[0266] This example provides an image processing method, including:

[0267] Acquire images, the images include objects, including but not limited to human bodies;

[0268] Detect the torso node and limb node of the human body, where the torso node and / or limb node can be 3D nodes, represented by 3D coordinates; the 3D can include 2D coordinates detected from the 2D image, and then use the 2D coordinates to The 2D coordinates obtained by the conversion algorithm of the 3D coordinates; the 3D coordinates may also be the 3D coordinates extracted from the 3D images collected by the 3D camera. The limb nodes here can include: upper limb nodes and / or lower limb nodes; nodes, fingertip nodes; the positions of these nodes reflect the movement of the hand and fingers

[0269] Convert the torso node into a quaternion representing the movement of the torso, which can be called a torso quaternion;

[0270] Convert the limb node into a quaternion representing the movement of the limb, ...

example 3

[0278] This example provides an image processing method that includes:

[0279] Acquire an image, the image contains a target, and the target can be a human body;

[0280] According to the image, the 3D posture of the target in the three-dimensional space is obtained, and the 3D posture can be represented by the 3D coordinates of the skeleton nodes of the human body;

[0281] Obtain the absolute rotation information of the joints of the human body in the camera coordinate system, and the absolute rotation position can be determined by the coordinates in the camera coordinate system;

[0282] According to the coordinates, the coordinate direction of the joint is obtained;

[0283]According to the hierarchical relationship, the relative rotation information of the joint is determined, and the determination of the relative parameter may specifically include: determining the position of the node of the joint relative to the root node of the human body; the relative rotation infor...

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 discloses an image processing method and device, image equipment and a storage medium. The image processing method comprises: acquiring an image; acquiring first rotation information of a node of a target based on the image; determining second rotation information of sub-nodes relative to father nodes in the nodes of the target according to the hierarchical relationship between the nodes and the first rotation information; and based on the second rotation information, controlling the motion of the corresponding node in the controlled model.

Description

[0001] This application claims the priority of the Chinese application with the application number 201910049830.6 and the filing date of January 18, 2019. technical field [0002] The present invention relates to the field of information technology, in particular to an image processing method and device, image equipment and a storage medium. Background technique [0003] With the development of information technology, users can conduct online lectures, web anchors, and somatosensory games through video recording. But in some cases, for example, somatosensory games require users to wear special somatosensory devices to detect their own limbs and other activities in order to control game characters. When conducting online lectures or webcasting, the user's face or body is completely exposed on the network, which may involve user privacy issues on the one hand, and information security issues on the other. In order to solve this privacy or security problem, the face image may ...

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): G06K9/00G06K9/46G06T7/00G06T7/20G06V10/24
CPCG06T7/0002G06T7/20G06T7/73G06T2207/30196G06T2207/20084G06V40/10G06V10/24G06V10/754G06V40/20G06V20/64G06V10/469G06F18/00G06T7/74G06T11/60G06T7/246G06T13/40G06T2200/04G06T2207/30201G06T7/0014G06V40/176
Inventor 汪旻刘文韬钱晨马利庄
Owner BEIJING SENSETIME TECH DEV CO LTD
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
Eureka Blog
Learn More
PatSnap group products