We present a real-time markerless human motion capture technique based on un-calibrated synchronized cameras. Training sets of real motions captured from marker based systems are used to learn an optimal pose manifold of human motion via Kernel Principal Component Analysis (KPCA). Similarly, a synthetic silhouette manifold is also learnt, and markerless motion capture can then be viewed as the ...

Ensemble clustering is a promising approach that combines the results of multiple clustering algorithms to obtain a consensus partition by merging different partitions based upon well-defined rules. In this study, we use an ensemble clustering approach for merging the results of five different clustering algorithms that are sometimes used in bioinformatics applications. The ensemble clustering ...

This paper presents approaches of incorporating subdivision techniques in the rendering process for computer-generated line drawings. A new method for accelerating silhouette detection is introduced. This “silhouette propagation” method gains its strength from being intertwined with the 3D subdivision process. Another technique reduces the number of 3D subdivision steps necessary for high-quali...

In this paper we present a new approach to high quality 3D object reconstruction by using well known computer vision techniques. Starting from a calibrated sequence of color images, we are able to recover both the 3D geometry and the texture of the real object. The core of the method is based on a classical deformable model, which defines the framework where texture and silhouette information a...

Most of volumetric 3D reconstruction methods need accurate silhouette information of foreground objects for the reliable 3D scene reconstruction of the objects. We present an approach to silhouette extraction based on our change detection method [1] using a statistical model and graph cuts based optimization. We describe some requirements for visual hull reconstruction. We show that our change ...

Silhouette recognition can reconstruct the three-dimensional pose of a human subject in monocular video so long as the camera’s view remains unoccluded by other objects. This paper develops a shape representation that can describe and compare partial shapes, extending the silhouette recognition technique to apply to video with occlusions. The new method operates without human intervention, and ...

Skeleton has been found a very useful feature in human motion analysis and gait recognition. However, it is usually hard to obtain the right feature skeleton because of shape variance of human silhouette and noise. Due to those reasons, unexpected skeleton branches will exist together with the main components of human body. To delete the unexpected branches, a silhouette reconstruction method i...

This paper proposes a method to estimate position of a small moving object. It is difficult to fit dynamic model of a target object moving fast and anomalously. We focuses on a phenomenon that a high-velocity moving object is observed as a line-shaped region in captured images by motion blur. Shapefrom-silhouette technique is applied to estimate the 3D trajectory of the observed lines. We choos...

Although an infinity of three-dimensional (3-D) objects could generate any given silhouette, we usually infer only one 3-D object from its two-dimensional (2-D) projection. What are the constraints that restrict this infinity of choices? We identify three mathematical properties of smooth surfaces plus one simple viewing constraint that seem to drive our preferred interpretation of 3-D shape fr...

clearly be used in nding the new set of cells and/or edges that needs to be visited in the grid, building the solution of the next silhouette query based on the solution of the previous query. (a) (b) Figure 9: A dinner scene. In (a), the polygonal model and in (b), the silhouette and boundary. bounded by O(n) and hence is in the same order of the magnitude of the input, large models can take f...