Reconstruction géométrique par estimation de posture

نویسندگان

  • Mathieu Barnachon
  • Brice Michoud
  • Erwan Guillou
  • Säıda Bouakaz
  • Saïda Bouakaz
چکیده

Geometrical reconstruction from multiple cameras can now concurrence classical reconstruction. Shape From Silhouette (SFS)[4] is a method that estimates the Visual Hull, in real time from observed silhouette in each view. Despite the fact that SFS is really simple and robust, it produces ghost parts : a set of 3D points that does not belong to real objects. These parts can significantly disturb the precision and the realism of the 3D shape. In this paper, we suggest to use the motion estimation of people, getting from motion capture, in order to remove these ghost parts and refine geometry. By construction, SFS gives a 3D hull of the filmed person. If we transform the computed geometry from original pose to the current pose, the intersection of reconstruction and observed pose produces a more precise reconstruction than the classical SFS. In this work, we introduce a real time and incremental approach, which automatically refines the 3D reconstruction of the acquired object.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Contrôle de l’approximation géométrique d’une interface par une métrique anisotrope

Dans cette Note, on présente une méthode pour contrôler l’approximation géométrique d’une variété de codimension 1 correspondant à une isovaleur d’une fonction scalaire u. On s’appuie sur la construction et l’adaptation d’une triangulation anisotrope à un champ de métrique riemannien tenant compte des propriétés intrinsèques de la variété. Un exemple d’adaptation anisotrope d’une triangulation ...

متن کامل

Online orientation distribution function reconstruction in constant solid angle and its application to motion detection in high angular resolution diffusion imaging

The di usion orientation distribution function (ODF) can be reconstructed from q-ball imaging (QBI) to map the complex intravoxel structure of water di usion. As acquisition time is particularly large for high angular resolution di usion imaging (HARDI), fast estimation algorithms have recently been proposed, as an on-line feedback on the reconstruction accuracy. Thus the acquisition could be s...

متن کامل

A Projective Framework for Structure and Motion Recovery from Two Views of a Piecewise Planar Scene

In this paper, we consider the problem of nding an optimal reconstruction from two views of a piecewise planar scene. We consider the general case of uncalibrated cameras, hence place us in a projective framework. In this case, there is no meaningful metric information about the object space that could be used to de ne optimization criteria. Taking into account that the images are then the only...

متن کامل

Automatic Alignment of Histological Sections for 3D Reconstruction and Analysis

In this report, we present a new method of aligning histological sections. First a displacement eld between the two images is computed by block matching. Then we estimate a rigid transformation based on the eld. The process is integrated within a multi-scale scheme. We carefully study the problem of robustness and we propose several ideas to deal with inter-section intensity di erences and back...

متن کامل

Voxel Data Based Marker-less Human Motion Capture Using Geometry Model

In this paper, we propose a novel approach for human posture estimation using geometry model. A volumetric reconstruction of a participant is obtained from multi-camera images. After definition of body model, the geometry model is fitted into the 3D human reconstructed volume. The gray theory, which is applicable to the prediction problem of a time-varying nonlinear system, is utilized to perfo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017