Method for reconstructing missing mark in motion capture

A motion capture and tagging technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as missing and missing motion capture tags

Pending Publication Date: 2021-11-02
黑龙江省科学院智能制造研究所
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to solve the problem of missing markers due to occlusion or ambiguity in the process of optical motion capture, and propose a method for reconstructing missing markers in motion capture

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 for reconstructing missing mark in motion capture
  • Method for reconstructing missing mark in motion capture
  • Method for reconstructing missing mark in motion capture

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0040] A method for reconstructing missing markers in motion capture according to this embodiment, the method for reconstructing missing markers is to estimate the position of missing markers from the incomplete data by combining the motion data and the human body's own joint constraints through the Kalman filter framework, and Reconstruction of the human skeleton model; including the following steps:

[0041] the step of analyzing the control position distribution of existing marker points to exclude non-linear directional movement;

[0042]Steps to eliminate noise and jitter based on the Kalman filter framework;

[0043] The step of calculating the position of the missing mark according to the constant speed sampling and recovering the missing data;

[0044] Combined with the topological model of the human skeleton, the steps of reconstructing the human motion model.

specific Embodiment approach 2

[0045] The difference from Embodiment 1 is that in this embodiment, a method for reconstructing missing markers in motion capture, the step of calculating the position of the missing markers based on constant-speed sampling includes:

[0046] 1), the current frame f t The state of the middle mark point and the previous frame f t-1 Analyze and compare the state of the middle mark point, if there is a rapid change in the difference, it is determined that there is a missing mark; where the rapid change in the difference is expressed as:

[0047] |f t -f t-1 |>δ (1)

[0048] In the formula, δ represents the threshold value;

[0049] 2), using the Kalman filter framework, using its position velocity constant rate model to predict the position of the missing marker, where the constant velocity model is expressed as:

[0050]

[0051] where f t and are the position and velocity of the marker at time t, respectively;

[0052] The predicted state in Kalman filtering is expr...

specific Embodiment approach 3

[0057] The difference from Embodiment 1 or Embodiment 2 is that in this embodiment, a method for reconstructing missing markers in motion capture, in the step of reconstructing the human motion model in combination with the topological model of the human skeleton, the human skeleton is obtained through the rigid body tracking method For the pallet model, specifically:

[0058] calculating the three-dimensional coordinates of the marker by using the stereo triangulation of the two-dimensional projection images of at least two cameras with the marker, when the three-dimensional position of the marker is reconstructed, tracking the marker from one frame to the next frame to complete the three-dimensional tracking process; after that , infer the human skeleton through 3D marker tracking; after that, fit the bone to the anatomical structure of the subject by scaling the bone length, and complete the skeleton calibration process; where, through 3D marker tracking, infer the human ske...

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 method for reconstructing missing mark in motion capture, and belongs to the field of human body motion information capture. The problem of missing marks due to occlusion or ambiguity in an optical motion capture process is solved. The invention discloses a method for reconstructing a missing mark in motion capture, which comprises the following steps of estimating the position of a missing mark point from incomplete data through a Kalman filtering framework in combination with motion data and human body joint constraints, and reconstructing a human body skeleton model; analyzing control position distribution of existing mark points and excluding non-linear direction movement; eliminating noise and jitter based on a Kalman filtering framework; calculating the position of a missing mark according to constant-speed sampling, and recovering missing data; and reconstructing a human body motion model in combination with the human body skeleton topology model. The invention belongs to a method for automatically predicting lost or correcting corrupted data. Skeletal motion during a motion capture session is reconstructed in real time.

Description

technical field [0001] The invention relates to a method for reconstructing missing markers in motion capture. Background technique [0002] Motion capture is the technique of recording the movement of a subject in real life and converting it into digital data. It is widely used in the film and video game industry, as well as film and video game, medical and performing arts, etc. For example, in the movie Titanic, all computer-simulated character movements were created from motion-capture data. [0003] Of all the motion capture technologies, optical motion capture, for example, Vikon is the most commonly used for var-ious applications. A set of markers are attached to the object and tracked by a set of cameras. Passive systems typically use IR illuminators paired with each camera, and the markers are anti-reflective material to bounce IR back to the camera. Active systems are marked with LEDs. Both designs enable the camera to track the position of the marker, and to t...

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): G06T7/246G06T7/277G06T7/55G06T7/73
CPCG06T7/251G06T7/277G06T7/55G06T7/73G06T2207/10028G06T2207/20024G06T2207/20076G06T2207/30196G06T2207/10016
Inventor 王云龙杨东亮何昕丛晓丹宋昌江章军
Owner 黑龙江省科学院智能制造研究所
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