Presentations

The anomalies of power equipment can be founded using temperature changes compared to its normal state. In this paper we present a system for visualizing temperature changes between the thermal 3D model and the current status of the temperature from any viewpoint. Our approach is based on precomputed 3D RGB model and 3D thermal model of the target scene achieved with a RGB-D camera coupled with the thermal camera.

The anomalies of power equipment can be founded using temperature changes compared to its normal state. In this paper we present a system for visualizing temperature changes between the thermal 3D model and the current status of the temperature from any viewpoint. Our approach is based on precomputed 3D RGB model and 3D thermal model of the target scene achieved with a RGB-D camera coupled with the thermal camera.

We propose a novel system for visual overlay of 3D virtual object onto real environment observed by tablet PC with camera. This system allows us to visually simulate the layout of virtual 3D objects in the real environment captured by the tablet PC. For estimating the pose and position of the tablet PC, we propose and implement procedures using the captured image and using the motion sensor.

In computer vision area, 3D sensing technologies have extensively been studied. For making such technologies be used in practical applications, there are still a lot of difficulties to adapt real world problems. In this talk, I introduce my recent challenges on real world applications that can be solved by vision-based 3D sensing. One application is on-site information visualization using mixed and augmented reality, in which vision-based object/camera pose estimation plays an significant role. Other application is 3D-video/Free viewpoint video using multi-view sensing/capturing based on 3D modeling of target scenes.

大規模仮想化現実のための多視点ビデオ映像の記録法と，そのシステム構築について報告した．

拡張現実感のために，未校正カメラで撮影された実シーン上に，仮想物体が存在するかのように重畳表示するための幾何学的整合性を実現する新しい手法を提案し，実験により有効性を示した．

多視点画像からロボットの動作を追跡する手法を提案し，さらに実験によりその有効性を検証した．

因子分解法とEPI解析により，環境の三次元復元を行う手法を提案し，実験により有効性を検証した．

距離画像とカラー画像を融合することにより，対象物体の三次元モデルを再構成する手法を提案し，実験により有効性を検証した．