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

Method and system for synthesizing images of object motion gestures

A technology of object motion and motion posture, applied in the field of image processing, can solve problems such as high cost and heavy workload

Active Publication Date: 2019-12-24
BEIJING HUAJIE IMI TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the embodiments of the present invention is to provide a method and system for synthesizing images of motion postures of objects to at least solve the problem of heavy workload and high cost caused by the collection and calibration of training data completely dependent on real data in the prior 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
  • Method and system for synthesizing images of object motion gestures
  • Method and system for synthesizing images of object motion gestures
  • Method and system for synthesizing images of object motion gestures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The specific implementation manners of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation manners described here are only used to illustrate and explain the embodiments of the present invention, and are not intended to limit the embodiments of the present invention.

[0023] Estimating poses from images is currently the key direction of pattern recognition. The most effective way is to estimate poses based on deep learning, but deep learning relies most on massive sample data. The embodiment of the present invention proposes that the non-rigid body model can be driven based on the degree of freedom to simulate the motion of the real object, and then the simulated three-dimensional model in different postures is projected and rendered to generate depth images and color image data in corresponding postures; thus, Using the method of skeleton-driv...

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 the field of image processing. An embodiment of the present invention provides a method and system for synthesizing an image of an object's motion posture, wherein the synthesis method of the object's motion posture image includes: constructing a three-dimensional model of the target object, wherein the three-dimensional model has a built-in skeleton, and the skeleton configuration There are skeleton nodes corresponding to different skeleton positions; generating degrees of freedom according to a predetermined degree of freedom driving function and the skeleton nodes, and driving the three-dimensional model to move based on the degrees of freedom; and based on the three-dimensional model in a moving state The projected images of the target object are synthesized into motion gesture images. Therefore, by using the skeleton-driven motion model, the image data of the object can be reversely and automatically synthesized when the attitude parameters of the object are known, which can greatly reduce the workload of collecting and calibrating data at low cost.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for synthesizing images of motion postures of objects. Background technique [0002] In recent years, AR (Augmented Reality, Augmented Reality) interactive applications have gradually entered daily life, and posture tracking of moving objects is an important part of 3D perception. The depth map can provide three-dimensional position information and provide a good basis for the attitude recovery of moving objects, but the popularity of depth sensors is still not enough, so the current attitude estimation of moving three-dimensional objects is through two sets of schemes: depth map or color map. Commonly used moving object attitude data samples are generally obtained using the following two methods: [0003] Solution 1: First, use a real sensor (depth camera or RGB camera) to collect sample data in different poses; then, manually calibrate the key points (pixel ...

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): G06T17/20G06K9/00
CPCG06T17/20G06V40/28
Inventor 王行盛赞周晓军李骊杨淼李朔
Owner BEIJING HUAJIE IMI TECH CO LTD