Mark-point-free visual motion capturing method based on three purposes

A motion-capture, markerless technology for computer vision that can solve high cost problems

Active Publication Date: 2021-05-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The more infrared cameras are installed, the more accurate the reconstructed human motion is, and the less affected by occlusion, but the cost is higher

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
  • Mark-point-free visual motion capturing method based on three purposes
  • Mark-point-free visual motion capturing method based on three purposes
  • Mark-point-free visual motion capturing method based on three purposes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] 1. The hardware system of the present invention is composed of three cameras, the angle between the cameras is θ, the height is h, the distance between the cameras and the human body is d, and the field of view of the cameras is The human body moves within the common range of the three-camera field of view. The acquisition environment background needs to be set to a single background, such as green, and the object to be reconstructed is wearing tight clothing, and the color of the clothing is quite different from the background color, so as to facilitate the extraction of human body contours. The three cameras need to be calibrated before capturing data to obtain their respective camera internal reference matrix K 0 ,K 1 ,K 2 It is used to correct the subsequent 2D and 3D joint point coordinates.

[0038] 2. Contour extraction. Contour extraction is carried out using the existing image segmentation technology. Since the background color is different from that of th...

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 mark-point-free visual motion capturing method based on three purposes, and belongs to the field of computer vision. Compared with the existing vicon system, the method provided by the invention only needs three visual cameras to capture a video sequence, only needs a tester to wear tight clothes and trousers, and does not need to paste a reflective mark on a human body; the obtained human body motion is not only the motion of joint points but the motion of the whole human body shape. Compared with the prior art, the performance and the reliability are improved, the cost is reduced, and the process is simplified. The technology of the invention requires fewer hardware equipment cameras; motions generally captured in the prior art are three-dimensional points, while the actions captured in the invention are three-dimensional grids including the body type and posture of a human body.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a three-purpose visual motion capture method based on a three-purpose point without markers. Background technique [0002] Motion capture has a wide range of needs in the fields of film and television animation production, and is usually realized by using inertial motion sensors and visual sensors. Among them, the precision of motion capture by using an inertial motion sensor is low, and the precision of motion capture by an optical sensor is high. The optical motion capture system represented by vicon uses 4 or more high-speed infrared cameras to collect passive luminescent markers attached to the joints of the human body, and uses the method of visual measurement to construct 3D data of human joint motion, which has been obtained in the industry. mature application. In order to obtain accurate and complete information about the joints of the human body, reflective balls must be...

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 Applications(China)
IPC IPC(8): G06T7/194G06T7/215G06T7/246G06N3/08
CPCG06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30196G06T7/194G06T7/215G06T7/251
Inventor 郑亚莉郑旭
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap