Misc - AMANO Toshiyuki

A Study of Perceptual Color Gamut Expansion for Optical See-Through Displays

秋山 諒, 山本 豪志朗, 天野 敏之, プロプスキ アレクサンダー, 藤本 雄一郎, 神原 誠之, 加藤 博一

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 ( 電子情報通信学会 )  119 ( 386 ) 49 - 53   2020.01

Manipulation of material perception with light-field projection

Toshiyuki Amano

Proceedings of SPIE - The International Society for Optical Engineering   10997   2019.01

　View Summary

© 2019 SPIE. Reflected illumination from a surface provides a variety of information about material perception. A precisely designed illumination projection with a video projector changes the reflected illumination, and it manipulates our material perception, apart from the apparent texture and color. In this paper, several works on perceptual material appearance manipulation that employ projector-camera systems are presented. Psychophysics-based image processing algorithms that utilize co-axial optical configuration facilitate successive manipulation. In our latest work, viewing-direction-dependent appearance manipulation using light-field projection on an anisotropic reflection surface is proposed for advanced material perception manipulation.

DOI

New Evaluation Method of the Appearance Control Using the Camera and Projector Optical System

石川 貴史, 前田 擁平, 池田 佑輔, 牛田 俊, 天野 敏之

システム制御情報学会研究発表講演会講演論文集 ( システム制御情報学会 )  60   3p   2016.05

書作品への光投影による作者意図の拡張表現の試み

山本豪志朗, 天野敏之

映像情報メディア学会技術報告   40 ( 11(AIT2016 42-136) ) 9 - 12   2016.03

懐中電灯型プロジェクタカメラ系による視覚補助に関する研究

天野敏之

立石科学技術振興財団助成研究成果集   ( 24 ) 12 - 16   2015.09

色補正技術の応用 まるでイリュージョン! 光沢&透明感! 物体の見え方を変化させる照明 (特集 ぴったり! ラズベリー・パイ×モバイル時代プロジェクタ) -- (はじめての本格プロジェクション・マッピング)

天野 敏之

インターフェース = Interface ( CQ出版社 )  41 ( 5 ) 101 - 110   2015.05

交差反復処理による深度カメラと地面のなす角度の推定

郎 彦昆, 呉 海元, 天野 敏之, 陳 謙

第77回全国大会講演論文集   2015 ( 1 ) 521 - 522   2015.03

　View Summary

This paper proposes a principle statistical approach for GP (ground plane) detection by using depth camera. Current GP detection algorithms have focused on calculating the minimum distance to estimating the ground plane, while less of them have considered the probability distribution and the angle of the camera to improve the performance.In this paper, we employ the KDE (Kernel Density Estimator) to obtain the probability density of the height distribution, with which the GP can be estimated. By using the estimated GP we calculate the angle of camera, and then feedback it to update GP until a certain condition has been reached. We evaluate our algorithm named as AGP-CIC(Angle-GP cross iterative convergence) on many challenging scenes and compare it with other distance-based algorithms.

A Coordinated Projector Camera Control for the Omnidirectional Appearance Manipulation

天野 敏之, 島名 功, 牛田 俊

日本バーチャルリアリティ学会大会論文集 Proceedings of the Virtual Reality Society of Japan, Annual Conference ( [日本バーチャルリアリティ学会] )  19   458 - 461   2014.09

Adaptive geometrical compensation of projection image by update the pixel map

Shouhei Kasaya, Toshiyuki Amano, Masaki Ohtsuki

IPSJ SIG Notes. CVIM ( Information Processing Society of Japan (IPSJ) )  2014 ( 22 ) 1 - 6   2014.02

　View Summary

The Spatial Augmented Reality using the projector and camera system enables the geometrical compensation of the projection image based on the pixel correspondence (pixel map) between a capture image and a projection image obtained by the calibration. However, an artifact pattern is generated by a projection image because of a disparity between the pixel map and a physical projection when the projection is changed. In this paper, we propose the geometrical calibration method that update the pixel map adaptively. The idea is it uses the artifact pattern, and calculates the optical flow between a projection image and a capture image based on epipolar constraint.

Online photometric calibration for the mobile projector camera system

Takahiro Kawaguchi, Toshiyuki Amano, Masaki Ohtsuki

IPSJ SIG Notes. CVIM ( Information Processing Society of Japan (IPSJ) )  2014 ( 21 ) 1 - 6   2014.02

　View Summary

The spatial augmented reality technique that consists of a projector and a camera enables the appearance manipulation of real world by the illumination projection. Today, since the projector keeps getting smaller, the SAR made composed by mobile devices became a realistic story. However, it is difficult to calibrate an optical response beforehand because the use in various illumination environment is supposed for the mobile SAR system. In this research, we propose the method that achieves an invariant appearance manipulation for the various ambient lighting by the accurate reflectance estimation using DLP projector.

Projection Based Real-time Material Perception Manipulation

天野 敏之

日本バーチャルリアリティ学会大会論文集 Proceedings of the Virtual Reality Society of Japan, Annual Conference ( [日本バーチャルリアリティ学会] )  18   234 - 237   2013.09

Shading illusion:プロジェクタカメラ系による陰影制御-印刷媒体での新しい立体表現-

天野敏之

画像の認識・理解シンポジウム2012論文集     2012

ユーザの嗜好を考慮した情報推薦のためのSkyline演算の拡張

吉武亮, 宮崎純, 藤澤誠, 天野敏之, 加藤博一

平成23年度 情報処理学会関西支部 支部大会 講演論文集   2011   2011.09

SNS-based volunteer support system for disaster recovery

平松 達也, 藤澤 誠, 天野 敏之

ヒューマンインタフェース学会研究報告集 ( ヒューマンインタフェース学会 )  12   41 - 46   2010

Experiments using 100 Objects : Comparison of Pose Representations for Pose Estimations

TANAKA Satoko, HARADA Kengo, TAMAKI Toru, RAYTCHEV Bisser, KANEDA Kazufumi, AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  109 ( 249 ) 127 - 132   2009.10

　View Summary

We report a result of an experimental study on properties of pose representations for 3DOF linear pose estimations with 100 CG objects. We use linear regression as a pose estimation method. First, we explain a method of linear pose estimation and two properties of pose representations. Next, we use four pose representations (rotation matrix, ZYX Euler angle, exponential map, and quaternions), for pose estimation experiments, and compare estimation errors. We show that estimation error of rotation matrix is significantly smaller than other representations by using pairwise t-test.

ICPR 2008

天野 敏之

日本バーチャルリアリティ学会誌 = Journal of the Virtual Reality Society of Japan   14 ( 1 ) 43 - 44   2009.03

An Appearance Based Fast Linear Pose Estimation

AMANO Toshiyuki, TAMAKI Toru

Proc IAPR Conf Mach Vis Appl   11th   182-186   2009

Linear 3-D Object Pose Estimation with Dense Sample Images-Discussions about Limitation of Parameter Estimation Ability by the Linear Regressions-

AMANO Toshiyuki, TAMAKI Toru

Proc IAPR Conf Mach Vis Appl   11th   287-290   2009

会場担当より

神原 誠之, 天野 敏之, 池田 聖, 藤澤 誠

日本バーチャルリアリティ学会誌 = Journal of the Virtual Reality Society of Japan   13 ( 4 ) 219 - 220   2008.12

Accuracy change according to the number of learning samples for view-based pose estimation

奥川 裕之, 原田 健吾, 玉木 徹, 天野 敏之, 金田 和文

第10回IEEE広島支部学生シンポジウム(HISS)論文集 ( IEEE広島支部学生シンポジウム(HISS) )    98 - 71   2008.11

画像の学習に基づく姿勢推定手法の学習サンプル数と精度の関係性の検討

奥川裕之, 原田健吾, 玉木徹, 天野敏之, 金田和文

電気・情報関連学会中国支部連合大会講演論文集(CD−ROM) ( 電気・情報関連学会中国支部 )  59th ( 59 ) 470 - 470   2008.10

Linear 3D object pose estimation with dense sample images

玉木 徹, 天野 敏之

MIRU 2008 画像の認識・理解シンポジウムダイジェスト     501 - 501   2008.07

　View Summary

In the image parameter estimation by the linear regression, it has very high degrees of freedom for the decision of regression coefficients, because the dimension of image vector is huge high. In this paper, we propose a sequential regression coefficient calculation algorithm, and we realize its calculation for dense samples with reasonable computational cost. Moreover, we apply this method to the pose estimation of the 3-D object, and we discuss about limit of parameter estimation ability by the linear regression with the coil-20 image library.

Representing pose by spherical functions for pose estimation

玉木 徹, 天野 敏之, 金田 和文

MIRU 2008 画像の認識・理解シンポジウムダイジェスト     502 - 502   2008.07

　View Summary

We propose a novel representation of pose in 3 degrees-of-freedom (DOF) for view-based pose estimation. First we show that a conventional representation of pose in 1 DOF is a Fourier basis, and extend the observation to 2 DOF with spherical harmonics. Then we represent 3 DOF pose with spherical functions that are continuous on SO(3), and give transformations from the spherical functions representation to a quaternion and a rotation matrix.

Expanding images of an object under 3DOF rotation with spherical functions and its applications to image interpolation and pose estimation

玉木 徹, 天野 敏之, 金田 和文

MIRU 2008 画像の認識・理解シンポジウム論文集     1169 - 1174   2008.07

　View Summary

We propose an implementation for expanding images of an object under 3 DOF rotation with spherical functions, an orthonormal basis on SO(3), and describe its applications to image interpolation and pose estimation.

Representing pose by spherical functions for pose estimation

玉木 徹, 天野 敏之, 金田 和文

MIRU 2008 画像の認識・理解シンポジウム論文集     1134 - 1141   2008.07

　View Summary

We propose a novel representation of pose in 3 degrees-of-freedom (DOF) for view-based pose estimation. First we show that a conventional representation of pose in 1 DOF is a Fourier basis, and extend the observation to 2 DOF with spherical harmonics. Then we represent 3 DOF pose with spherical functions that are continuous on SO(3), and give transformations from the spherical functions representation to a quaternion and a rotation matrix.

Expanding images of an object under 3DOF rotation with spherical functions and its applications to image interpolation and pose estimation

玉木 徹, 天野 敏之, 金田 和文

MIRU 2008 画像の認識・理解シンポジウムダイジェスト     507 - 507   2008.07

　View Summary

We propose an implementation for expanding images of an object under 3 DOF rotation with spherical functions, an orthonormal basis on SO(3), and describe its applications to image interpolation and pose estimation.

A Tracking Method using Multi-core CPUs for Virtual 3D Pop-up Books

TAMURA Ryosuke, AMANO Toshiyuki, KATO Hirokazu

IPSJ SIG Notes. CVIM ( Information Processing Society of Japan (IPSJ) )  2008 ( 3 ) 341 - 342   2008.01

　View Summary

Virtual pop-up books are systems which can overlay a captured image with 3D CG objects based on augmented reality technology. 3D geometrical consistency in the composite image can be kept by estimating the relative pose of the camera from the physical book. We have been studying about this pose estimation method using feature tracking based on template matching. Since multi-core CPUs have been spread in recent years, it can be easily achieved to improve the performance speed by parallel processing on a standard PC environment. We modified our tracking codes for parallel processing by multi-core CPUs and improved the performance speed and robustness of the tracking.

A Tracking Method using Multi-core CPUs for Virtual 3D Pop-up Books

TAMURA Ryosuke, AMANO Toshiyuki, KATO Hirokazu

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers )  107 ( 427 ) 121 - 122   2008.01

　View Summary

Virtual pop-up books are systems which can overlay a captured image with 3D CG objects based on augmented reality technology. 3D geometrical consistency in the composite image can be kept by estimating the relative pose of the camera from the physical book. We have been studying about this pose estimation method using feature tracking based on template matching. Since multi-core CPUs have been spread in recent years, it can be easily achieved to improve the performance speed by parallel processing on a standard PC environment. We modified our tracking codes for parallel processing by multi-core CPUs and improved the performance speed and robustness of the tracking.

PRMU Algorithm Contest 2007 "Let's Make Jigsaw Puzzle! -Image Reconstruction by Matching-" Summary Report and Prize Winning Algorithms

AMANO Toshiyuki, TAMAKI Toru, MURAKAMI Takenori, AOKI Yasuaki, BITO Koji, AKIMA Yuuta, ARAKI Kousuke, SAKO MASASHI, HANAOKA Shouhei

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  107 ( 384 ) 125 - 136   2007.12

　View Summary

This article gives a summary report on the algorithm contest titled "Let's Make Jigsaw Puzzle! -Image Reconstruction by Matching-", which is sponsored by PRMU (Pattern Recognition and Media Understanding) Technical Group of IEICE-ISS, with brief overviews of prize-winning algorithms provided by the winners. The contest in this year asked for the algorithms that solve the arrangement of pieces for the image reconstruction. The total number of applications is 84, and the brilliant 7 algorithms have won the prizes.

PRMU Algorithm Contest 2007 "Let's Make Jigsaw Puzzle! -Image Reconstruction by Matching-" Summary Report and Prize Winning Algorithms

AMANO Toshiyuki, TAMAKI Toru, MURAKAMI Takenori, AOKI Yasuaki, BITO Koji, AKIMA Yuuta, ARAKI Kousuke, SAKO MASASHI, HANAOKA Shouhei

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  107 ( 384 ) 125 - 136   2007.12

　View Summary

This article gives a summary report on the algorithm contest titled "Let's Make Jigsaw Puzzle! -Image Reconstruction by Matching-", which is sponsored by PRMU (Pattern Recognition and Media Understanding) Technical Group of IEICE-ISS, with brief overviews of prize-winning algorithms provided by the winners. The contest in this year asked for the algorithms that solve the arrangement of pieces for the image reconstruction. The total number of applications is 84, and the brilliant 7 algorithms have won the prizes.

On methods for taking pedstrians' paths for prediction

篠村 祐司, 原野 友敬, 玉木 徹, 天野 敏之, 金田 和文, 内田 誠一

第9回IEEE広島支部学生シンポジウム(HISS)論文集 ( IEEE広島支部学生シンポジウム(HISS) )    2007.11

Defect Detection Using k-means Clustering and Eigenspace Outlier Detector

AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  107 ( 281 ) 111 - 116   2007.10

　View Summary

In this paper, a new approach of defect detection from complex texture patterns that have structural regularity for automated visual inspection is proposed. The approach uses correlation based defect detection, and any kind of model of defect feature is unnecessary. Additionally, proposed method applies k-means clustering to the samples acquired by pixel-by-pixel movement of sampling window, and achieves a very sensitive defect detection. In the experiment, the effectiveness is shown through the experiment by the complex texture patterns that have structural regularity.

コンパクトな辞書データによる高速な3次元物体認識と姿勢推定

木村将之, 天野敏之, 玉木徹, 梅崎太造

電気関係学会東海支部連合大会講演論文集(CD−ROM)   2007   ROMBUNNO.O-387   2007.09

On the complex and quaternion subspaces for view-based pose estimation

TAMAKI TORU, AMANO TOSHIYUKI, KANEDA KAZUFUMI, ICHIHARA YUMIKO

IPSJ SIG Notes. CVIM ( Information Processing Society of Japan (IPSJ) )  160 ( 87 ) 181 - 186   2007.09

　View Summary

This paper proposes a new method for construction of a complex subspace for rotation about a single axis and a quaternion subspace for 3DOF rotation of a 3D object, then demonstrates with the proposed method view-based pose estimation.

On the complex and quaternion subspaces for view-based pose estimation

TAMAKI TORU, AMANO TOSHIYUKI, KANEDA KAZUFUMI, ICHIHARA YUMIKO

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  107 ( 207 ) 181 - 186   2007.08

　View Summary

This paper proposes a new method for construction of a complex subspace for rotation about a single axis and a quaternion subspace for 3DOF rotation of a 3D object, then demonstrates with the proposed method view-based pose estimation.

Projecting images of rotating object onto complex subspace by the matrix of cyclic group and its application

玉木 徹, 天野 敏之, 金田 和文

MIRU2007 画像の認識・理解シンポジウム ダイジェスト ( 画像情報フォーラム )    563 - 563   2007.07

Projecting images of rotating object onto subspace by block diagonalization of the matrix of cyclic group and its application

玉木 徹, 天野 敏之, 金田 和文

MIRU2007 画像の認識・理解シンポジウム ダイジェスト ( 画像情報フォーラム )    562 - 562   2007.07

Projecting images of rotating object onto subspace by block diagonalization of the matrix of cyclic group and its application

玉木 徹, 天野 敏之, 金田 和文

MIRU 2007 画像の認識・理解シンポジウム論文集 ( 画像情報フォーラム )    982 - 987   2007.07

　View Summary

This paper proposes a linear map that projects images of an rotating object about an axis onto a subspace where the rotation of the object is represented with many simple rotations in two dimensional subspaces. First we consider a cyclic group that permutates the image sequence, then construct a matrix of the cyclic group by multiplication of low rank matrices with block diagonalization. We demonstrate interpolation of the image sequence by rotation in the subspace, and discuss the ability of the proposed linear map onto the subspace.

Prediction of a path of pedestrian using combination of Eigenspace and null space

篠村 祐司, 玉木 徹, 天野 敏之, 金田 和文

MIRU 2007 画像の認識・理解シンポジウム論文集 ( 画像情報フォーラム )    774 - 779   2007.07

　View Summary

This paper proposes a method for Eigenspace-based prediction of a person's path in future with current path. This method uses projection and back projection of the current path onto Eigenspace. However, the prediction does not take the nature of a path of pedestrian and results in non-smooth path. The proposed method modify the prediction by using null vectors in the orthocomplement of the learned Eigenspace and adding linear combinations of the null vectors to the prediction so that the path becomes smooth. Coe?cients of the linear combinations are computed by decent gradient method. Some experimental results on actual pathes are shown.

Projecting images of rotating object onto complex subspace by the matrix of cyclic group and its application

玉木 徹, 天野 敏之, 金田 和文

MIRU 2007 画像の認識・理解シンポジウム論文集 ( 画像情報フォーラム )    988 - 993   2007.07

　View Summary

This paper proposes a linear map that projects images of an rotating object about anax is onto a complex subspace where the rotation is represented with an simple rotation in one dimensional complex space. First we consider a cyclic group that permutates the image sequence, then construct a complex matrix of the cyclic group by multiplication of low rank matrices. We demonstrate interpolation of the image sequence by rotation in the subspace ,and discuss the ability of the proposed linear map onto the complex subspace.

On a pose estimation in a subspace with block diagonalization of cyclic transient matrix of an image sequence

玉木 徹, 天野 敏之, 金田 和文

MIRU2007 画像の認識・理解シンポジウム論文集 ( 画像情報フォーラム )    958 - 963   2007.07

　View Summary

This paper proposes a new method for estimation of pose of a 3D object rotating about an axis by using a subspace with block diagonalization of a cyclic transient matrix of the image sequence of the object. The proposed method searches the pose parameter with the distance between an image and the standard image multiplied with a block diagonal matrix in the subspace. Alternative method that directly estimates the pose parameter as an angle subtended by two vectors in two-dimensional subspace. Experimental results with a real image sequence demon-strate that the maximum estimation error is about 4[deg], and 1.23[deg] in average, which show the effectiveness of the proposed method.

On a pose estimation in a subspace with block diagonalization of cyclic transient matrix of an image sequence

玉木 徹, 天野 敏之, 金田 和文

MIRU2007 画像の認識・理解シンポジウム ダイジェスト ( 画像情報フォーラム )    558 - 558   2007.07

3D object recognition for dictionary minimization and high-speed processing

KIMURA Masayuki, AMANO Toshiyuki, TAMAKI Toru, UMEZAKI Taizo

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  107 ( 57 ) 85 - 90   2007.05

　View Summary

In this paper, a method to recognize 3-D object in parallel is proposed as the improvement of the EbC method that is a parameter estimation solution such as posture of the 3-D objects. The proposed method can realize high-speed object recognition with maintaining small learning data to compares an unknown object image with two image vectors, called EbC image pairs, provided every object by learning. In other words, the proposed method uses the property that projection points of target images are corresponding to circular edge of a plane that generated by EbC image Pair. In recognition experiment, recognition performance of proposed method was verified using COIL-20. Moreover, the effectiveness of the proposal method was considered from comparison with the recognition result in the CLAFIC method that is the method known well conventionally.

Prediction of a path of pedestrian using Eigenspace and correction with the null space

SHINOMURA Yuji, TAMAKI Toru, AMANO Toshiyuki, KANEDA Kazufumi

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  106 ( 605 ) 25 - 30   2007.03

　View Summary

This paper proposes a method for Eigenspace-based prediction of a person's path in future with current path. This method uses BPLP proposed by Amano et. al.: projection and backprojection of the current path onto Eigenspace. However, the prediction does not take the nature of a path of pedestrian and results in non-smooth path. The proposed method modify the prediction by using null vectors in the orthocomplement of the learned Eigenspace and adding linear combinations of the null vectors to the prediction so that the path becomes smooth. Coefficients of the linear combinations are computed by decent gradient method. Some experimental results on actual pathes are shown.

A Report on MIRU2006 Young Researchers' Program

AMANO Toshiyuki, IWAMURA Masakazu, OKABE Takahiro, KATO Tsuyoshi, TAMAKI Toru, UCHIDA Seiichi, UCHIDA Seiichi

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  106 ( 429 ) 73 - 84   2006.12

　View Summary

MIRU Young Researchers' Program was held in conjunction with MIRU2006 symposium for promoting exchanges between young researchers in CV and PR. This report gives a summary of the program.

マルチポート固有空間法

玉木 徹, 天野 敏之

部分空間法研究会 Subspace 2006 ( 部分空間法研究会 )    7 - 15   2006.07

　View Summary

本稿では、多様体の教師付き問題としての姿勢パラメータ推定手法である「マルチポート固有空間法」[1],[2]について議論する。これは欠損画素の輝度値を推定して画像を補間するBPLP[3],[4]を基にしており、群の回帰問題を空間への投影という線形演算で行うものである。まずマルチポート固有空間法の内容を説明し、その主要部分は連立方程式による最小ノルム推定であることを示す。またその方程式による空間への投影がどのようなものかを説明し、学習とサンプル数の影響について述べる。

Estimation-by-Completion : 3次元物体の線形姿勢推定手法

天野 敏之, 玉木 徹

MIRU 2006 画像の認識・理解シンポジウムダイジェスト ( 電子情報通信学会 )    373 - 373   2006.07

　View Summary

MIRU2006 画像の認識・理解シンポジウム インタラクティブセッション優秀賞受賞

Estimation-by-Completion : A linear method for pose estimation of 3D object

天野 敏之, 玉木 徹

MIRU 2006 画像の認識・理解シンポジウム論文集 ( 電子情報通信学会 )    460 - 465   2006.07

　View Summary

In this paper, we propose a method called EbC, Estimation-by-Completion, a high speed estimation of pose parameters of a three-dimensional object in an image. For appearance-based pose estimation, EbC method introduces the concept of information track that represents the parameters embedded into image samples. The pose parameters are estimated by the completion of the information track with BPLP method, an image interpolation technique with eigenspace learning. EbC integrates the completion of the information track and the estimation of the parameters into pairs of two images, called EbC image pairs, and performs quickly the estimation by few inner products of images. Experimental results for pose estimation results of three degree of freedoms, rotation about vertical axis and horizontal and vertical translations, show the accuracy, and calculation cost of EbC method is described.

Virtual Recovery of the Depleted Art Object based on AR Technology

SUZUKI Ryo, AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  105 ( 612 ) 73 - 78   2006.02

　View Summary

Today, for the positioning of the modern work of art the irreversible restoration that aims recover of the beauty is not allowed in the many cases. In this research, we propose the virtual beauty recover method by using AR technology for this problem and realize the virtual beauty recover on the real objects. In the proposed method, the texture image for color compensation is generated beforehand and this image is projected on the art by the LCD projector. Moreover, the luster restoration by the image projection that based on the phong model was realized is also reported.

Virtual Recovery of the Depleted Art Object based on AR Technology

SUZUKI Ryo, AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  105 ( 614 ) 73 - 78   2006.02

　View Summary

Today, for the positioning of the modern work of art the irreversible restoration that aims recover of the beauty is not allowed in the many cases. In this research, we propose the virtual beauty recover method by using AR technology for this problem and realize the virtual beauty recover on the real objects. In the proposed method, the texture image for color compensation is generated beforehand and this image is projected on the art by the LCD projector. Moreover, the luster restoration by the image projection that based on the phong model was realized is also reported.

Document Interface Using Augmented Reality

KUNDA Satoshi, AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  105 ( 614 ) 79 - 84   2006.02

　View Summary

This Paper proposed a new document interface "smart paper interface" in consideration of affordance that printout paper document has. The final goal of "smart paper interface" is to realize the seamless handling between computerized document and real document. Therefore, the affordance of paper was achieved with projection method of the computerized document to the real document and comment method by using Pad Holder with the camera, projector system.

Document Interface Using Augmented Reality

KUNDA Satoshi, AMANO Toshiyuki

IEICE technical report ( The Institute of Electronics, Information and Communication Engineers )  105 ( 612 ) 79 - 84   2006.02

　View Summary

This Paper proposed a new document interface "smart paper interface" in consideration of affordance that printout paper document has. The final goal of "smart paper interface" is to realize the seamless handling between computerized document and real document. Therefore, the affordance of paper was achieved with projection method of the computerized document to the real document and comment method by using Pad Holder with the camera, projector system.

D-11-115 The Calibration of Pan-Tilt-Zoom Camera

Sugeda Shigehiko, Amano Toshiyuki

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2005 ( 2 ) 115 - 115   2005.03

D-11-130 An Approach for Image Crack Detection Based on Image Fractality

Hachisuka Jun, Amano Toshiyuki

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2005 ( 2 ) 130 - 130   2005.03

D-12-34 3D K-means tracking with multi camera : Interface with high compatibility in clerical work working environment

Sugimoto Hiroaki, Amano Toshiyuki

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2005 ( 2 ) 184 - 184   2005.03

A Report on MIRU Young Researchers' Program 2004

AMANO Toshiyuki, UKITA Norimichi, OKABE Takahiro, SAGAWA Ryusuke, HIURA Shinsaku

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers )  104 ( 524 ) 43 - 48   2004.12

　View Summary

MIRU Young Researchers' Program was held in conjunction with MIRU2004 symposium to boost exchanges between young researchers aiming at CV and PR. This report describes summary of the program.

A Report on MIRU Young Researchers’ Program 2004

天野敏之, 浮田宗伯, 岡部孝弘, 佐川立昌, 日浦慎作

電子情報通信学会技術研究報告 ( The Institute of Electronics, Information and Communication Engineers )  104 ( 524(PRMU2004 134-153) ) 43 - 48   2004.12

　View Summary

MIRU Young Researchers' Program was held in conjunction with MIRU2004 symposium to boost exchanges between young researchers aiming at CV and PR. This report describes summary of the program.

D-12-163 Virtual Of Painting Using Brush Stroke Restoration

Kunda Satoshi, Amano Toshiyuki

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2004 ( 2 ) 329 - 329   2004.03

D-11-91 Super Resolution Using BPLP Method on the Eigenspace

KAWAI Yasuhiro, AMANO Toshiyuki

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  91   91 - 91   2004

Image Interpolation by the High Dimensional Nonlinear Projection Using kBPLP Method

AMANO Toshiyuki, SATO Yukio

IEICE transactions on information and systems ( The Institute of Electronics, Information and Communication Engineers )  86 ( 4 ) 776 - 776   2003.04

　View Summary

In these years, nonlinear subspace method, kPCA and Support Vector Machine have attracted a great deal of interest. These nonlinear subspace methods can generate the nonlinear subspace for pattern distribution by using appropriate kernel function about the problem that class boundary on feature space has expressed by a hypersurface. Therefore these methods are able to high accurate pattern recognition. In this paper, we propose an image interpolation method that based on above nonlinear subspace methods. Concretely we applied the nonlinear subspace to BPLP method based on linear subspace and got the kernel BPLP method that is a high dimensional nonlinear projection.

The proposal of the reappearance technique of mouth form with difference vector, and examination

Watanabe Takumi, Iwata Tomohiro, Amano Toshiyuki, Sato Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2003 ( 2 ) 329 - 329   2003.03

Recognition of Auricle using Range Image

Ishibashi Masayuki, Amano Toshiyuki, Sato Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2003 ( 2 ) 332 - 332   2003.03

A Method of Automatic Facial Feature Point Extraction for 3-D Facial Model Generation

NAKAMURA Masanori, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2003 ( 2 ) 333 - 333   2003.03

3-D Head Model Generation using Dual Cubicscope System

KOYASU Takehiko, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2003 ( 2 ) 328 - 328   2003.03

Proposal of Cosmetic CAI Technique by Makeup Simulator

IGUCHI Atsushi, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2   261 - 261   2003

I-63 Restoration on the digital media of the degradation pictures by weathering

Yoshida Eiichiro, Amano Toshiyuki, Sato Yukio

情報科学技術フォーラム一般講演論文集 ( Forum on Information Technology )  2002 ( 3 ) 125 - 126   2002.09

Facial Movement Analysis with Iterative Mesh Adaptation

GUNARATNE Pujitha, AMANO Toshiyuki, SATO Yukio

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers )  101 ( 421 ) 21 - 26   2001.11

　View Summary

This paper presents a technique of analyzing the degree of movement in facial parts during expressions using range and intensity information. Pre-determined facial actions are measured by a rangefinder system called 'Cubicfacer' which produces dense 3D and color texture images of a measuring subject. A topological face mesh is constructed and adapted to the measured range data using the information in the corresponding color image. The mesh adaptation process is done iteratively by approximating a polynomial function with the least squares estimation. Patch variances of sub-meshes are then computed to analyze the movements of different facial parts. The experiment is done for apparent normal and disordered human subjects to determine the differences in facial movements.

Influence of Dummy Binocular Disparities and Monocular Clues on the Depth Perception

ARAKAWA Naofumi, ISHIKAWA Hiroyo, AMANO Toshiyuki, SATO Yukio

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers )  101 ( 421 ) 127 - 132   2001.11

　View Summary

The phenomenon in which depth feeling increases is known for many years by giving dummy binocular disparities to a single picture, and getting rid of the vergence. Although the reason is not solved yet, if solved, it is clear to take a big step toward realization of stereoscopic vision from a single picture. Then, towards realization of stereoscopic vision by the single picture, the influence on the depth perception which dummy binocular disparities and monocular clues do was investigated quantitatively. From the result, depending on the intensity of monocular clues, it became clear to enable depth perception of the same grade as the case where a stereo picture is used also by use of the picture which added dummy binocular disparities.

On Polyhedron Recognition Time and Object Image Entropy

HIGAKI Masashi, ISHIKAWA Hiroyo, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 229 - 229   2001.03

3D Slack Measurement of Face from Range Images

IGARASHI Toshio, AMANO Toshiyuki, HIROSE Osamu, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 299 - 299   2001.03

Portable Rangefinder System

SHOGO Hisanari, HASEGAWA Kazuhide, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 133 - 133   2001.03

Personal Identification using 3D Conchae Shape

MIYAMOTO Yuusuke, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 285 - 285   2001.03

3-D Hair Estimation using Two Range Images

KOYASU Takehiko, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 298 - 298   2001.03

Color Recovery Using Eigenspace Method

YOSHIDA Eiichirou, AMANO Toshiyuki, SATO Yukio

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2001 ( 2 ) 238 - 238   2001.03

3D Morphing using Standard Facial patch Model

Proceedings of the IECIE General Conference     2001

Strobe Rangefinder

Proceedings of the 7th Symposium on Sensing via Image Information     255 - 260   2001

Measurement System for 3-D Shape and Refrectance Parameters

Proceedings of the IECIE General Conference     2001

Development of The Next Generation Document Reader -EyeScanner-

Proceedings of the 7th Symposium on Sensing via Image Information     379 - 384   2001

Measurement of Visual Complexity with Effective Visual Field

SATO Kaname, AMANO Toshiyuki, SATO Yukio

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers )  100 ( 443 ) 35 - 40   2000.11

　View Summary

It is difficult to decide what kind of and how many visual information from figure characteristics for recognition. However, if a quantity of all visual information can be decided, we can decide kind and amount of visual information, and have a clue to make it clarify the mechanism of brain for visual information process. In this paper, we show the possibility of measurement of the Visual Complexity that is defined as a quantity of all figure characteristics in the object, which are source of visual information, with measurement of the Effective Visual Field for recognizing character, and Eyesight Distribution on Retina.

Object Recognition using the Weighted Eigen Space

INOSHITA Tetsuo, AMANO Toshiyuki, HIURA Shinsaku, INOKUCHI Seiji

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  2000 ( 2 ) 277 - 277   2000.03

固有空間法を用いたBPLPによる画像補間

天野敏之

MIRU 2000   1   217 - 222   2000

Extracting Facial Features from Range and Color Images

Proceedings of the Information and Systems Society Conference of IEICE     226   2000

Image Interpolation Using Eigenspace with BPLP Method

  1   217 - 222   2000

Object Search and Pose Detection Based on Eigenspace Approach

Proc. of the 2000 JapanUSA Flexible Automation Conference     CD-ROM Proceedings, F-04 SIGNAL PROCESSING 2000JUSFA-13104   2000

Eigenspace Matching Method and an Application against Lacked Data

AMANO Toshiyuki, INOKUCHI Seiji

Proceedings of the Society Conference of IEICE ( The Institute of Electronics, Information and Communication Engineers )  1999   176 - 176   1999.08

Object Tracking using the Eigen Space by Considering the background

INOSHITA Tetsuo, AMANO Toshiyuki, INOKUCHI Seiji

Proceedings of the Society Conference of IEICE ( The Institute of Electronics, Information and Communication Engineers )  1999   171 - 171   1999.08

Object Tracking using a small amount of movement projection on the Eigen Space

Proceedings of the IECIE General Conference     1999

Eigenspace approach for Object Detect using Range and Color Image

Proceedings of the IECIE General Conference     1999

Image Compression Using Edge Information

INOSHITA Tetsuo, AMANO Toshiyuki, YAMAGUCHI Akashi, INOKUCHI Seiji

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )  1998 ( 2 ) 28 - 28   1998.03

固有空間照合に基づく距離画像からの物体の姿勢検出--形状モデルを用いた仮想距離画像生成

天野 敏之, 山口 証, 井口 征士

画像ラボ ( 日本工業出版 )  9 ( 1 ) 10 - 14   1998.01

Eigenspace approach for a pose detection with range images.Virtual range image generation using shape model.

天野敏之, 山口証, 井口征士

画像ラボ ( 日本工業出版 )  9 ( 1 ) 10 - 14   1998.01

Eigenspace Approach for Object Recognition and its Pose Detection.

AMANO Toshiyuki, YAMAGUCHI Akashi, INOKUCHI Seiji

PRMU ( The Institute of Electronics, Information and Communication Engineers )  98 ( 10 ) 71 - 78   1998

　View Summary

Range-image is one of a useful data for the recognition and localization of freeform 3-D object. Most recognition and pose-detection methods from range-image have to use a feature extraction, but it is necessary a simply model and difficult to extract features. Besides central to this issue is the problem of feature matching on the object and range-image. So we proposed use of appearance-matching technique on the range-image. To use range image for the appearance-matching has one more advantage. Range-image expresses a geometrical object information. So, it is easy to make range-image from polygon data to using camera-parameter, and large numbers of sample images from reality measurement are not necessary. In the fact large number of sample is the key to use appearance-matching. In this paper we propose a methodology for the recognition and pose-detection of freeform 3-D object by appearance-matching on the range-image.

距離画像の固有空間照合法に基づく物体の姿勢検出-画素欠損画像に対するロバスト姿勢検出手法-

天野敏之

画像の認識 理解シンポジウム, 1996     205 - 210   1996

Eigen space approach for a pose detection with range images

Toshiyuki Amano, Shinsaku Hiura, Akashi Yamaguti, Seiji Inokuchi

Proceedings - International Conference on Pattern Recognition ( Institute of Electrical and Electronics Engineers Inc. )  1   622 - 626   1996

　View Summary

An application of the pose detection using range images usually uses characteristic matching of the geometrical model but this method has two problems: selecting characteristics from range images is difficult
and it is difficult to make a geometrical model for a complicated shape. Previously a parametric eigen-space method was proposed for pose detection. This method makes object recognition and pose detection possible, but this parametric eigen-space method has a problem that intensity-images depend on a variety of light conditions therefore learning images must include variation of light conditions. © 1996 IEEE.

DOI

Calibration Method for Silicon Range Finder

AMANO Toshiyuki, HIURA Shinsaku, SATO Kosuke, YOSHIGAHARA Takayuki, YOKOYAMA Atsushi, INOKUCHI Seiji

Proceedings of the IEICE General Conference ( The Institute of Electronics, Information and Communication Engineers )    413 - 414   1995

　View Summary

我々の開発したシリコンレンジファインダ(以下,SRF)はビデオカメラ以上の速度で距離画像を計測することの出来るデバイスであり,ビジュアルフィードバック等の動距離画像処理分野での応用が期待されている.このような3次元デバイスを実応用するためには柔軟性の高いキャリブレーション手法が必要であり,これまでにシステムパラメータによる方法が利用されてきた.しかしSRFは専用チップによりレーザ光を受光するため,シーンの明暗を計測することが出来ない.そのためプリズムを用いて同一レンズを通した画像を撮影することでカメラ系のキャリブレーション問題を解決した.また,プロジェクタ系に回転ミラーを用いているために,透視変換に基づく方法であるシステムパラメータ法を用いることが出来ない.そこで仮想スクリーンという概念を導入し,ミラーの回転角をプロジェクタ座標に補正することでシステムパラメータ表現を実現した.SRFをシステムパラメータによりキャリブレーションすることにより,各種応用分野への柔軟な対応が可能となった.