We describe a simple and robust algorithm for estimating 3D shape given a number of silhouette points obtained from two or more viewpoints and a parametric model of the shape. Our algorithm minimizes (in the least squares sense) the distances from the lines obtained by unprojecting the silhouette points to 3D to their closest silhouette points on the 3D shape. The solution is found using an ite...

We have revisited the silhouette algorithm developed by Canny, and designed its new symbolic-numeric version. The symbolic-numeric silhouette algorithm do not require the symbolic computation of the determinants of resultant matrices, and can work on oating point arithmetic. Though its combinatorial complexity remains the same, but its algebraic complexity has been improved signi cantly which i...

In this paper we study the problem of shape from silhouette outlines (SFO) using a novel adaptive dandelion model. SFO reconstructs a 3D model using only the outmost silhouette contours and produces a solid called the ‘‘bounding hull’’. The dandelion model is composed of a pencil of organized line segments emitted from a common point which samples the bounding hull surface in regularly distribu...

We present an automatic system for retargeting a human body motion extracted from an image sequence into a new character in a still image. In contrast to analyzing the articulated motion of its skeleton in the previous vision-based human body tracking and posture recognition system, we use direct 2-D image warping based on a silhouette. At first, we represent the performer’s silhouette with the...

In this paper, a new feature called 3D edge oriented gradient histogram of slide blocks is proposed for human action recognition, based on the idea that the slide area of human body edge can be seen as a spatio-temporal silhouette surface when human performing a certain action in video. This feature is processed by defining dense 3D spatio-temporal slide blocks on the spatio-temporal silhouette...

We show how periodic motions can be represented by a small number of eigenshapes that capture the whole dynamic mechanism of the motion. Spectral decomposition of a silhouette of a moving object serves as a basis for behavior classification by principle component analysis. The boundary contour of the walking dog, for example, is first computed efficiently and accurately. After normalization, th...