We present a multi-view alpha matting method that requires no user input and is able to deal with any arbitrary scene geometry through the use of depth maps. The algorithm uses multiple observations of the same point to construct constraints on the true foreground color and estimate its transparency. A novel free viewpoint rendering pipeline is also presented that takes advantage of the generat...

In this paper we address the issue of change after deployment in safety-critical embedded system applications. Our goal is to substitute lab-based verification with in-field formal analysis to determine whether an update may be safely applied. This is challenging because it requires an automated process able to handle multiple viewpoints such as functional correctness, timing, etc. For this pur...

In this paper we present an algorithm for the synthesis of multi viewpoint images at non-intermediate positions, based on stereoscopic images. We consider the synthesis of images from virtual camera positions and the synthesis of images for scene reconstruction using stereo displays. The algorithm provides scene reconstruction without geometric distortion and without any restriction to the posi...

あらまし 複数のセンサから得られる観測データや,マルチモーダルな特徴量からなる複数の時系列データを 統合しながら,ジェスチャーなどの動的事象を識別するモデルとして,「Integrated Continuous State Machine (ICSM)」を提案する.これは,各特徴系列を個別に識別する状態遷移モジュールをそれぞれ用意し,それを連 続状態空間において動的に統合するものであり,各モジュールの信頼性を逐次計算することにより,クラスの識 別にとってより重要な入力へ,動的にフォーカスを切り替えることが可能となる.本論文では,統合に適したモ ジュールとして,連続状態空間 (実ベクトル空間) 中での状態遷移によってクラス識別を行う Continuous State Machines (CSM)を導入し,続いて,複数の CSM間における,状態の共起性に基づいた相互作用を導入する. 連続状...

Abstract The database object that describes tens of attributes is referred as high dimensional data space. In high dimensional data, the common distance measures can be influenced by noise. Existing clustering algorithms are implemented based on partitioning, hierarchical, density based and grid based. These methods assume some kind of cluster relationship among the clustered objects. Similarit...

A newly developed high-performance multiimager VGA camera array is described. Designed for synchronization, bandwidth, and economy within a videoconferencing application, and demonstrated initially through novel video mosaicking, the system shows promise for accelerating the new field of multi-viewpoint imaging. We describe the camera system’s design, control, performance characteristics, use i...

This paper presents an approach for empowering collaborative workspaces through ultra-high-resolution tiled display environments concurrently interfaced by multiple multi-touch devices. Multi-touch table devices are supported along with portable multi-touch tablet and phone devices, which can be added to and removed from the system on the fly. Events from these devices are tagged with a device ...

We propose a system for robust modeling and visualisation of complex outdoor scenes from multi-camera image sequences and additional sensor information. A camera rig with one or more fire-wire cameras is used in conjunction with a 3-axis rotation sensor to robustly obtain a calibration of the scene with an uncalibrated structure from motion approach. Dense depth maps are estimated with multi-vi...