DEVICE AND METHOD FOR RECONSTRUCTING HUMAN POSTURE AND SHAPE MODEL ON BASIS OF MULTI-VIEW IMAGE BY USING INFORMATION ON RELATIVE DISTANCE BETWEEN JOINTS

Provided are a device and a method for reconstructing a human posture and shape model on the basis of a multi-view image by using information on a relative distance between joints. A human model reconstruction method according to an embodiment of the present invention comprises: extracting encoded t...

Full description

Saved in:
Bibliographic Details
Main Authors YOON, Ju Hong, KIM, Je Woo, PARK, Min Gyu
Format Patent
LanguageEnglish
French
Korean
Published 23.12.2021
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Provided are a device and a method for reconstructing a human posture and shape model on the basis of a multi-view image by using information on a relative distance between joints. A human model reconstruction method according to an embodiment of the present invention comprises: extracting encoded two-dimensional human posture information pieces from multi-view images, respectively, and converting same into encoded three-dimensional human posture information pieces; and fusing the converted information pieces into one encoded three-dimensional human posture information piece, and simultaneously reconstructing a three-dimensional human posture and shape. By the method, even though a specific joint is not detected, the entire posture can be reconstructed by means of information on the distance from surrounding joints. L'invention concerne un dispositif et un procédé permettant de reconstruire un modèle de forme et de posture humaine sur la base d'une image multivue en utilisant des informations concernant une distance relative entre des articulations. Un procédé de reconstruction de modèle humain selon un mode de réalisation de la présente invention consiste : à extraire des éléments d'information de posture humaine bidimensionnelle codée à partir d'images multivue, respectivement, et à les convertir en éléments d'information de posture humaine tridimensionnelle codée ; et à fusionner les éléments d'informations convertis en un seul élément d'information de posture humaine tridimensionnelle codé, et à reconstruire simultanément une posture et une forme humaines tridimensionnelles. Au moyen du procédé, même si une articulation spécifique n'est pas détectée, l'ensemble de la posture peut être reconstruite au moyen d'informations concernant la distance vis-à-vis des articulations environnantes. 관절 간 상대 거리 정보를 이용한 다시점 영상 기반 사람 자세 및 형상 모델 복원 장치 및 방법이 제공된다. 본 발명의 실시예에 따른 사람 모델 복원 방법은, 다시점 영상들로부터 인코딩된 사람의 2차원 자세 정보들을 각각 추출하여 인코딩된 사람의 3차원 자세 정보들로 각각 변환하고, 하나의 인코딩된 사람의 3차원 자세 정보로 융합하여 사람의 3차원 자세와 형상을 동시에 복원한다. 이에 의해, 특정 관절이 검출되지 않더라도 주변 관절들로부터의 거리 정보를 이용하여 전체 자세를 복원할 수 있게 된다.
Bibliography:Application Number: WO2020KR17833