Faculty Profiles - MIGITA Tsuyoshi

Presentations -

Division display 61 - 80 of about 101 ／ All the affair displays >>

RGBD画像を用いた人物姿勢追跡の高速化と人体モデルパラメータ推定への適用

長谷康平, 溝部諒, 右田剛史, 尺長健

情報処理学会研究報告(Web) 2015

パーティクルフィルタとLevenberg-Marquardt法による顔・人物姿勢追跡の検討

筒井健斗, 溝部諒, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2015

3d face tracking and recognition for depth-image sensor

片山聡一朗, 中岸久佳, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2013.1.23 The Institute of Electronics, Information and Communication Engineers

形状・反射特性・光源の同時推定法の改良と様々な実画像への適用

槌谷洋介, 右田剛史, 尺長健

情報処理学会研究報告(CD-ROM) 2013

Stereoscopic Shape Reconstruction from Image Sequence using Spline Interpolation

2012.1.12

Implementation and Evaluation of Simultaneous Estimation of Shape, Reflectance and Lighting

右田剛史, 槌谷洋介, 尺長健

情報処理学会研究報告(CD-ROM) 2012

Simultaneous Estimation of Shape, Reflectance Property and Lightng Conditions based on Complementary Space of Light Color

祖川和弘, 右田剛史, 尺長健

情報処理学会研究報告(CD-ROM) 2011

Specular-Free Residual Minimization for Photometric Stereo with Unknown Light Sources.

Tsuyoshi Migita, Kazuhiro Sogawa, Takeshi Shakunaga

Advances in Image and Video Technology - 5th Pacific Rim Symposium 2011 Springer

Recovery of Facial Shape based on Simultaneous Estimation of Shape, Reflectance Property and Light Position

澤見幸枝, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2010

Stereoscopic Reconstruction of Facial Shape with a Spline Surface

永井雄大, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2010

Tracking 3d Pose of Rigid Object by Sparse Template Matching.

Yuki Oka, Toshiyuki Kuroda, Tsuyoshi Migita, Takeshi Shakunaga

Proceedings of the Fifth International Conference on Image and Graphics(ICIG) 2009 IEEE Computer Society

Simultaneous Recovery of Reflectance Property, Shape and Light Position based on Torrance-Sparrow Model

OGINO Shinsuke, MIGITA Tsuyoshi, SHAKUNAGA Takeshi

IEICE technical report 2008.3.10 The Institute of Electronics, Information and Communication Engineers

Event date： 2008.3.10

Language：Japanese

Given a set of images, where a point light source moves around an object, we can formulate recovery of the reflectance property, texture and shape of the object, as well as the positions of the light source. We herein describe an efficient algorithm to address this large-scale nonlinear optimization problem. Various objects, including toy models and human faces, are successfully recovered without any special devices nor a precise calibration.

researchmap

Report on 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)

OKATANI Takayuki, SUGIMOTO Shigeki, HIURA Shinsaku, MUKAIGAWA Yasuhiro, KINOSHITA Koichi, NISHIYAMA Masashi, MIGITA Tsuyoshi, OKUTOMI Masatoshi

IPSJ SIG Notes. CVIM 2008.1.17 Information Processing Society of Japan (IPSJ)

Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position.

Tsuyoshi Migita, Shinsuke Ogino, Takeshi Shakunaga

Computer Vision - ECCV 2008 2008 Springer

Efficient Object Tracking with 3D Sparse Template in Coarse-to-fine Search

岡裕希, 黒田利行, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2008

Efficient Sparse Template Tracking along with Directional Integral Matching

黒田利行, 大森誠, 児玉健二, 右田剛史, 尺長健

電子情報通信学会技術研究報告 2008

Evaluation of Epipole Estimation Methods with/without Rank-2 Constraint across Algebraic/Geometric Error Functions.

Tsuyoshi Migita, Takeshi Shakunaga

2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007)(CVPR) 2007 IEEE Computer Society

One Dimensional Epipole Search based on Point Correspondences in Two Uncalibrated Views

MIGITA Tsuyoshi, SHAKUNAGA Takeshi

IEICE technical report 2006.3.17 The Institute of Electronics, Information and Communication Engineers

Event date： 2006.3.17

Language：Japanese

The fundamental matrix can be estimated from 7 or more point correspondences in two uncalibrated views, and essentially it is an epipole search in 2-dimensional space (hemisphere). However, since the corresponding cost function is a non-linear one, unique solution is not guaranteed. While the well-known 8-point algorithm gives an approximate solution, neglecting the rank constraint on the fundamental matrix, we strictly take the constraint into account and obtain a better solution. Specifically, we reduce the problem into a high-order polynomial equation in one variable, which is satisfied by the ratio (e.g. x/z) of all the optimal or locally optimal epipole coordinates (x, y, z). We also show a lower-order equation by introducing an approximation, which still outperforms the 8-point algorithm.

researchmap

Evaluation of the effect of rank-2 constraint on the accuracy of epipole estimation

右田剛史, 尺長健

情報処理学会研究報告 2006

One-Dimensional Search for Reliable Epipole Estimation.

Tsuyoshi Migita, Takeshi Shakunaga

Advances in Image and Video Technology(PSIVT) 2006 Springer

　 PREV - NEXT 　

< MIGITA Tsuyoshi >

Presentations -