Realistic Rendering and Animation of a Multi-Layered Human Body Model

Yeşil, Mehmet Šahin; Güdükbay, Uğur

doi:10.1109/iv.2006.89

Cited by 3 publications

(2 citation statements)

References 10 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D pose estimator computes the 3D joint configurations from the 2D joint coordinates and the depth information of the human model for each body part. Finally, the 3D human model is animated based on the 3D joint configurations computed from the video sequence [27,28]. We use forward kinematics to generate the human posture according to the calculated joint angles.…”

Section: Motion Capture and Animation Systemmentioning

confidence: 99%

Motion capture and human pose reconstruction from a single-view video sequence

Güdükbay

Demir

Dedeoğlu

2013

Digital Signal Processing

View full text Add to dashboard Cite

Cataloged from PDF version of article.We propose a framework to reconstruct the 3D pose of a human for animation from a sequence of single-view video frames. The framework for pose construction starts with background estimation and the performer's silhouette is extracted using image subtraction for each frame. Then the body silhouettes are automatically labeled using a model-based approach. Finally, the 3D pose is constructed from the labeled human silhouette by assuming orthographic projection. The proposed approach does not require camera calibration. It assumes that the input video has a static background, it has no significant perspective effects, and the performer is in an upright position. The proposed approach requires minimal user interaction. (C) 2013 Elsevier Inc. All rights reserved

show abstract

Section: Motion Capture and Animation Systemmentioning

confidence: 99%

Motion capture and human pose reconstruction from a single-view video sequence

Güdükbay

Demir

Dedeoğlu

2013

Digital Signal Processing

View full text Add to dashboard Cite

show abstract

“…Some methods were based on passive 2D images and others were found on active 3D surface measurement systems. Much research had dealt with the region of human hand (Magnenat-Thalmann et al, 1988), leg (Lamousin and Waggenspack, 1994), facial animation (Kahler et al, 2003), human organ reconstruction (Yu et al, 2005) and whole-body model (Yesil, 2003). Moreover, there was considerable interest in modeling human body in the clothing industry (Stylios et al, 2001;Xu et al, 2002;Kurokawa, 1997).…”

Section: Introductionmentioning

confidence: 99%

An approach to predicting bra cup dart quantity in the 3D virtual environment

Wang

Zhang²

2007

International Journal of Clothing Science and Technology

View full text Add to dashboard Cite

Purpose -The aim of this paper is to explore a method of predicting the amount of personalized bra cup dart in the 3D virtual environment for supporting the made-to-measure research of the optimum fitted brassiere pattern design. Design/methodology/approach -Very useful enhanced FFD (free-form-deformation) techniques used in both computer animation and geometric modeling were skillfully transplanted to the female breast model deformation. Meanwhile, on the basis of 3D scan and surface modeling technologies, the realization approach of the abstract female breast model library focusing on the individual variations of shapes and sizes was presented. Then according to the principle of isometric area and flabellate segments, the personalized bra cup dart quantity and its distributive information were provided by 3D-2D transformation. Findings -The paper finds that personalized female breast shapes and various aesthetic breast forms sculpted by different bras could be interactively simulated. Accordingly, the amount of corresponding individual bra cup dart and its distributive information were provided. The cup darts were mainly distributed below the bust line. Moreover, dart shapes were curvy.Research limitations/implications -The principles of virtual breast library construction and 3D-2D transformation are also suitable for other parts of the human body such as buttocks, abdomen and, etc. for intimate apparel research. Originality/value -The method of predicting the personalized bra cup dart quantity based on the 3D virtual breast model library was delivered for the first time. The novel findings provided an important guideline for designers to improve the well-fitted bra pattern design technique. Furthermore, it would reduce the manufacturing cost without keeping physical dummies.

show abstract