DSpace/Manakin Repository

著者 "Yokoya, Naokazu" のブラウズ:

著者 "Yokoya, Naokazu" のブラウズ:

ソート項目: ソート順: 表示件数:

  • Kawai, Norihiko; Inoue, Naoya; Sato, Tomokazu; Okura, Fumio; Nakashima, Yuta; Yokoya, Naokazu (一般社団法人情報処理学会, 2014-09-15)
    This paper proposes a background estimation method from a single omnidirectional image sequence for removing undesired regions such as moving objects, specular regions, and uncaptured regions caused by the camera's blind ...
  • Kume, Hideyuki; Sato, Tomokazu; Yokoya, Naokazu (Elsevier, 2015-05-19)
    In this paper, a new pipeline of structure-from-motion for ground-view images is proposed that uses feature points on an aerial image as references for removing accumulative errors. The challenge here is to design a method ...
  • Sato, Tomokazu; Kanbara, Masayuki; Yokoya, Naokazu; Takemura, Haruo (Kluwer Academic Publishers, 2002-01-01)
    Three-dimensional (3-D) models of outdoor scenes are widely used for object recognition, navigation, mixed reality, and so on. Because such models are often made manually with high costs, automatic 3-D reconstruction has ...
  • Kawai, Norihiko; Sato, Tomokazu; Yokoya, Naokazu (IEEE, 2016-03-01)
    Diminished reality aims to remove real objects from video images and fill in the missing regions with plausible background textures in realtime. Most conventional methods based on image inpainting achieve diminished reality ...
  • Kawai, Norihiko; Yamasaki, Masayoshi; Sato, Tomokazu; Yokoya, Naokazu (社団法人映像情報メディア学会, 2013-10-01)
    This paper proposes a new diminished reality technique which removes AR markers from a user's view image. In order to achieve natural marker hiding, three factors should be considered; (1) naturalness of texture generated ...
  • Sato, Tomokazu; Yokoya, Naokazu (Elsevier, 2010-02-16)
    In this article, we propose an efficient method for estimating a depth map from long-baseline image sequences captured by a calibrated moving multi-camera system. Our concept for estimating a depth map is very simple; we ...
  • Okura, Fumio; Ueda, Yuko; Sato, Tomokazu; Yokoya, Naokazu (社団法人映像情報メディア学会, 2014-01-01)
    This paper proposes a free-viewpoint interface for mobile-robot teleoperation, which provides viewpoints that are freely configurable by the human operator head pose. The viewpoints are acquired by a head tracker equipped ...
  • Fabian, Lorenzo Dayrit; Nakashima, Yuta; Sato, Tomokazu; Yokoya, Naokazu (Springer, 2015-12-07)
    Standard video does not capture the 3D aspect of human motion, which is important for comprehension of motion that may be ambiguous. In this paper, we apply augmented reality (AR) techniques to give viewers insight into ...
  • Okura, Fumio; Kanbara, Masayuki; Yokoya, Naokazu (ACM, 2015-03-05)
    This article describes a Mixed-Reality (MR) application that superimposes lost buildings of a historical site onto real scenes virtualized using spherical aerial images. The proposed application is set at a UNESCO World ...
  • Sato, Tomokazu; Hiroyuki, Koshizawa; Yokoya, Naokazu (International Journal of Virtual Reality, 2009-12-03)
    This paper proposes a method to render free viewpoint images from omnidirectional videos using a deformable 3-D mesh model. In the proposed method, a 3-D mesh is placed in front of a virtual viewpoint and deformed by using ...
  • Takafumi, Taketomi; Sato, Tomokazu; Yokoya, Naokazu (Elsevier, 2011-05-10)
    In the field of augmented reality (AR), many kinds of vision-based extrinsic camera parameter estimation methods have been proposed to achieve geometric registration between real and virtual worlds. Previously, a feature ...
  • Vallerand, Steve; Kanbara, Masayuki; Yokoya, Naokazu (一般社団法人電子情報通信学会, 2004-06-01)
    In order to perform the registration of virtual objects in vision-based augmented reality systems, the estimation of the relation between the real and virtual worlds is needed. This paper presents a three-point vision-based ...
  • Kawai, Norihiko; Machikita, Kotaro; Sato, Tomokazu; Yokoya, Naokazu (一般社団法人情報処理学会, 2010-11-15)
    Omnidirectional multi-camera systems cannot capture entire fields of view because of their inability to view areas directly below them. Such invisible areas in omnidirectional video decrease the resulting realistic sensation ...
  • 町田, 貴史; 竹村, 治雄; 横矢, 直和 (一般社団法人情報処理学会, 2006-06-15)
    実環境に仮想物体を合成表示する複合現実感において,より写実性の高い表現を行うために現実物体を仮想化する仮想化現実の研究がさかんに行われている.特に,物体の表面反射特性を推定することは実環境と仮想化された物体との間の陰影矛盾を解決するために重要である.近年,この問題に対する1つの解決法としてインバースレンダリングが注目されており,著者らは,物体の距離画像と表面のテクスチャ画像から物体の反射特性を密に推定する研究を行ってきた.また複雑な形状 ...
  • 中里, 祐介; 神原, 誠之; 横矢, 直和 (日本バーチャルリアリティ学会, 2005-09-30)
    To realize an augmented reality (AR) system using a wearable computer, the exact position and orientation of a user are required. We propose a localization method which is based on using an IR camera and invisible visual ...
  • 牧田, 孝嗣; 神原, 誠之; 横矢, 直和 (一般社団法人電子情報通信学会, 2006-08-21)
  • 天目, 隆平; 神原, 誠之; 横矢, 直和 (日本バーチャルリアリティ学会, 2005-09-30)
    By realizing augmented reality on wearable computers, it becomes possible to overlay annotations on the real world based on user's current position and orientation. However, it is difficult for the user to understand links ...
  • 池谷, 彰彦; 佐藤, 智和; 池田, 聖; 神原, 誠之; 中島, 昇; 横矢, 直和 (一般社団法人電子情報通信学会, 2005-08-01)
    本論文では,手持ちのビデオカメラで紙面を撮影した動画像から,紙面とカメラの三次元的な位置関係を表すカメラ外部パラメータを推定し,これに基づいて紙面のモザイク画像を生成する手法を提案する.カメラ外部パラメータ推定に基づく本手法は,初期フレームにおいてカメラが紙面に対して傾いている場合でも,正対したモザイク画像を生成できるという特徴をもつ.本手法では,はじめに,各フレームのカメラ外部パラメータを特徴点追跡結果から推定する.次に,映像から一度 ...
  • 池谷, 彰彦; 佐藤, 智和; 池田, 聖; 神原, 誠之; 中島, 昇; 横矢, 直和 (一般社団法人電子情報通信学会, 2004-08-20)
  • 河合, 紀彦; 佐藤, 智和; 横矢, 直和 (一般社団法人電子情報通信学会, 2008-09-01)
    本論文では,写真についた傷など画像内の不要な部分を取り除き,その欠損領域を自動的に修復する新たな手法を提案する.従来,欠損領域の修復に関しては,欠損領域と欠損領域以外のデータ領域のパターン類似度を用いて欠損領域全体のもっともらしさを表す目的関数を定義し,それを最適化することで画像修復を行う手法が提案されている.しかし,従来提案されている目的関数の最適化による修復では,以下に挙げる二つの問題により不自然なテクスチャが生じやすい.( 1 ...

サイト検索

ブラウズ

登録利用者