Conference Activities & Talks -

Experimental study on properties of pose representations for 3DOF linear pose estimations

原田 健吾, 玉木 徹, 金田 和文, 天野 敏之

MIRU 2009 画像の認識・理解シンポジウム論文集  2009.07  

　View Summary

We report a result of an experimental study on properties of pose representations for 3DOF linearpose estimations. We use linear regression as a pose estimation method. First, we explain a method of linear poseestimation and two properties of pose representations. Next, we use four pose representations (rotation matrix, ZYX Euler angle, exponential map, and quaternion), and consider whether each pose representation satisfy the properties. We show that only rotation matrix satises the properties, and verify experimentally that rotation matrix has the smallest error.

Real world dynamic appearance enhancement with procam feedback

Toshiyuki Amano, Hirokazu Kato

PROCAMS 2008 - ACM/IEEE 5th International Workshop on Projector Camera Systems  2008.12.01  

　View Summary

In this paper, a dynamic appearance enhancement method for the less saturated object is proposed. The appearance enhancement method proposed in this paper is realized with a projector camera dynamic feed back system. Therefore, the proposed method has an ability of the rapid and continuous appearance enhancement and it is useful for the human visual perception assistance. Also, the system not requires a pre-captured appearance of the target © 2008 ACM.

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  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)  2008.10.25  

Analysis of Causes of Failure in the Natural Feature Tracking for Augmented Reality

田村亮輔, 天野敏之, 加藤博一

日本バーチャルリアリティ学会大会論文集(CD-ROM)  2008.09.24  

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  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.

Linear 3D object pose estimation with dense sample images

玉木 徹, 天野 敏之

MIRU 2008 画像の認識・理解シンポジウム論文集  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.

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  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・理解シンポジウムダイジェスト  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.

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  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.

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  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

田村亮輔, 天野敏之, 加藤博一

情報処理学会研究報告  2008.01.17  

　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  2008.01.10  

　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.

Comparative study of path nomalizations for path prediction

Proc. Of 14th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2008)  2008  

Experimental study on performance of view-based pose estimation

Proc. Of 14th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2008)  2008  

実世界ダイナミックアピアランス強調システム

画像の認識・理解シンポジウム 2008 論文集  2008  

仮想立体絵本のためのマルチコアCPUによるトラッキング，A Tracking Method using Multi-core CPUs for Virtual 3D

第24回複合現実感研究会  2008  

プロジェクタカメラフィードバック系によるアピアランス強調

画像の認識・理解シンポジウム 2008 論文集  2008  

Appearance Enhancement Using a Projector-Camera Feedback System

International Conference on the Pattern Recognition, Proc. of 19th ICPR  2008  

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  2007.11