A Human Pose Sparse Reconstruction Method Based on Key Markers

A technology of sparse reconstruction and marking points, which is applied in the field of 3D graphics and virtual reality, can solve the problems of complex calculation process of inverse kinematics and unnatural posture, so as to avoid complex calculation process of inverse kinematics, reduce industrial costs, Effects to avoid unnatural results

Active Publication Date: 2015-08-26
ZHEJIANG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the traditional inverse kinematics (Inverse Kinematics), in the case where the positions of the end nodes of the human body are known, the kinematic formula is used to solve the underdetermined nonlinear system to calculate the parameter configuration of all the relevant nodes of the human body, even if anthropometric aspects are added constraints, the calculation process of inverse kinematics is still very complicated, and the final calculated pose may not be natural enough
This is where the power of a data-driven approach backed by pre-captured motion data emerges

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 Human Pose Sparse Reconstruction Method Based on Key Markers
  • A Human Pose Sparse Reconstruction Method Based on Key Markers
  • A Human Pose Sparse Reconstruction Method Based on Key Markers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The purpose and effects of the present invention will become more apparent by describing the present invention in detail below in conjunction with the accompanying drawings.

[0023] like figure 1 As shown, the present invention based on key marker points 3D human body motion gesture sparse reconstruction method comprises the following steps:

[0024] Step 1: Download the pure human motion database.

[0025] The motion data in the database is pure human motion data without any noise collected by sophisticated commercial equipment. Can directly use the 3D human motion database provided by Carnegie Mellon University (available from http: / / mocap.cs.cmu.edu Download), the database contains a variety of different types of motion collected from different people, such as running, walking, jumping and various physical activities.

[0026] Step 2: Use a motion capture device to capture low-dimensional control point signals.

[0027] Using the Vicon motion capture system ( ...

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 key mark point-based human body posture sparse reconstruction method. The method comprises the following steps of: extracting articulation point information corresponding to a key mark point to construct a k-d tree index for human body exercise data in a database; looking up k neighbors which are most matched with a control signal input by each frame in the database for the control signal input by each frame; constructing a recovery dictionary by the neighbors; and recovering the exercise posture of the whole body by utilizing a sparely expressed optimal frame and incorporating a result recovered by a previous frame into smoothness constraint of the current frame, wherein the recovered missing key point information is natural enough and no jitter exists in time sequence.

Description

technical field [0001] The invention relates to the fields of three-dimensional graphics and virtual reality, in particular to a sparse reconstruction method of human body posture. Background technique [0002] Human body motion capture technology has been widely used in entertainment fields such as animation production, film special effects, computer games, etc., bringing huge economic benefits. Although various commercial capture systems have been able to track and record human motion with high spatio-temporal resolution, due to the need for very high-cost software, equipment and data acquisition process (wearing is troublesome, commercial equipment usually requires users to wear 40‐ 50 carefully placed reflective markers, or 18 magnetic or inertial sensors), in addition, they usually have special requirements and restrictions on the performers and the collection environment, making them unsuitable for home use. [0003] In some home entertainment applications, it is not ...

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): G06T17/00G06F17/30
Inventor 肖俊林海庄越挺
Owner ZHEJIANG UNIV
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