Faculty Profiles - Nakazawa Atsushi

A puppet interface for retrieval of motion capture data Reviewed

Naoki Numaguchi, Atsushi Nakazawa, Takaaki Shiratori, Jessica K. Hodgins

Proceedings - SCA 2011: ACM SIGGRAPH / Eurographics Symposium on Computer Animation 157 - 166 2011

Language：English

Intuitive and efficient retrieval of motion capture data is essential for effective use of motion capture databases. In this paper, we describe a system that allows the user to retrieve a particular sequence by performing an approximation of the motion with an instrumented puppet. This interface is intuitive because both adults and children have experience playacting with puppets and toys to express particular behaviors or to tell stories with style and emotion. The puppet has 17 degrees of freedom and can therefore represent a variety of motions. We develop a novel similarity metric between puppet and human motion by computing the reconstruction errors of the puppet motion in the latent space of the human motion and those of the human motion in the latent space of the puppet motion. This metric works even for relatively large databases. We conducted a user study of the system and subjects could find the desired motion with reasonable accuracy from a database consisting of everyday, exercise, and acrobatic behaviors. Copyright © 2011 by the Association for Computing Machinery, Inc.

DOI： 10.1145/2019406.2019427

Scopus

Display-Camera Calibration from Eye Reflections

NITSCHKE Christian, NAKAZAWA Atsushi, TAKEMURA Haruo

The IEICE transactions on information and systems (Japanese edetion) 93 ( 8 ) 1450 - 1460 2010.8

Language：Japanese Publisher：The Institute of Electronics, Information and Communication Engineers

平面ディスプレイを光源とみなし,光源パターンを様々に変化させた対象の画像をカメラで撮影し形状復元やHCIに利用する,ディスプレイ・カメラシステムの研究が行われている.このような用途ではディスプレイとカメラの幾何校正を行うことが必要であり,従来法では球面ミラー等の付加的なデバイスを必要とした.本論文ではこれに対し,ユーザの眼球の表面反射を利用することで,特殊なデバイスを必要とせず校正を実現する手法を提案する.本手法ではディスプレイでパターンを投影し,その反射した像をカメラで撮影することでディスプレイ座標とカメラ座標の対応関係を得る.次に,この対応関係と眼球モデル,及びディスプレイサイズの情報を用いて最適化を行うことで解を得る.11名の被験者を用いた実験及びディスプレイとカメラを様々な位置関係で配置した状況に対する実験を行い,本手法の有効性及び様々な状況下での性能を明らかにした.

MMM-classification of 3D Range Data

AGRAWAL Anuraag, NAKAZAWA Atsushi, TAKEMURA Haruo

IEICE technical report 109 ( 470 ) 193 - 198 2010.3

Language：Japanese Publisher：The Institute of Electronics, Information and Communication Engineers

This paper presents a method for accurately segmenting and classifying 3D range data into particular object classes. Object classification of input images is necessary for applications including robot navigation and automation, in particular with respect to path planning. To achieve robust object classification, we propose the idea of an object feature which represents a distribution of neighboring points around a target point. In addition, rather than processing raw points, we reconstruct polygons from the point data, introducing connectivity to the points. With these ideas, we can refine the Markov Random Field (MRF) calculation with more relevant information with regards to determining "related points". The algorithm was tested against five outdoor scenes and provided accurate classification even in the presence of many classes of interest.

Display-Camera Calibration from Eye Reflections

NITSCHKE Christian, NAKAZAWA Atsushi, TAKEMURA Haruo

Technical report of IEICE. PRMU 109 ( 470 ) 205 - 210 2010.3

Language：Japanese Publisher：The Institute of Electronics, Information and Communication Engineers

We present a novel technique for calibrating display-camera systems from reflections in the user's eyes. Display-camera systems enable a range of vision applications that need controlled illumination, including 3D object reconstruction, facial modeling and human computer interaction. One important issue, though, is the geometric calibration of the display, which requires additional hardware and tedious user interaction. The proposed approach eliminates this requirement by analyzing patterns that are reflected in the cornea, a mirroring device that naturally exists in any display-camera system. We introduce an optimization strategy that is able to refine eye and spherical mirror calibration results. When applied to the eye, it even outperforms spherical mirror calibration unoptimized. Furthermore, we obtain a robust estimation of eye poses which can be used for eye tracking applications. Despite the difficult working conditions, the calibration results are good and should be sufficient for many applications.

3次元ビデオの連結によるインタラクティブ3次元VRシステム--3次元ビデオグラフによる3Dビデオの実現

D-11-78 DISASTER RECOGNITION IN 3D RANGE DATA

Kawai Kentaro, Agrawal Anuraag, Nakazawa Atushi, Takemura Haruo

Proceedings of the IEICE General Conference 2010 ( 2 ) 78 - 78 2010.3

D-12-88 A Hand Cart Type 3D Reconstruction System using a Laser Range Finder and a Single Camera

Ohnishi Takayuki, Nitschke Christian, Nakazawa Atsushi, Takemura Haruo

Proceedings of the IEICE General Conference 2010 ( 2 ) 199 - 199 2010.3

中澤篤志

画像ラボ / 画像ラボ編集委員会編 20 ( 9 ) 12 - 17 2009.9

Modeling 3D Urban Environment with Registration between Laser Range Images and Google Maps Image

MATSUMURA Miki, AGRAWAL Anuraag, NAKAZAWA Atsushi, TAKEMURA Haruo

IEICE technical report 109 ( 88 ) 13 - 18 2009.6

Dance to Music Character Animation

NINOMIYA KEI, NAKAZAWA ATSUSHI, TAKEMURA HARUO

2009 ( 34 ) 1 - 8 2009.6

Categorization of motion capture data using emotional words

NUMAGUCHI NAOKI, NAKAZAWA ATSUSHI, TAKEMURA HARUO

2009 ( 35 ) 1 - 6 2009.6

Human video textures Reviewed

Matthew Flagg, Atsushi Nakazawa, Qiushuang Zhang, Sing Bing Kang, Young Kee Ryu, Irfan Essa, James M. Rehg

Proceedings of I3D 2009: The 2009 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games 199 - 206 2009

Language：English

This paper describes a data-driven approach for generating photorealistic animations of human motion. Each animation sequence follows a user-choreographed path and plays continuously by seamlessly transitioning between different segments of the captured data. To produce these animations, we capitalize on the complementary characteristics of motion capture data and video. We customize our capture system to record motion capture data that are synchronized with our video source. Candidate transition points in video clips are identified using a new similarity metric based on 3-D marker trajectories and their 2-D projections into video. Once the transitions have been identified, a video-based motion graph is constructed. We further exploit hybrid motion and video data to ensure that the transitions are seamless when generating animations. Motion capture marker projections serve as control points for segmentation of layers and nonrigid transformation of regions. This allows warping and blending to generate seamless in-between frames for animation. We show a series of choreographed animations of walks and martial arts scenes as validation of our approach. Copyright © 2009 by the Association for Computing Machinery, Inc.

DOI： 10.1145/1507149.1507182

Scopus

MMM-classification of 3D Range Data Reviewed

Anuraag Agrawal, Atsushi Nakazawa, Haruo Takemura

ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 2269 - + 2009

Language：English Publisher：IEEE

DOI： 10.1109/ROBOT.2009.5152539

Display-Camera Calibration from Eye Reflections Reviewed

Christian Nitschke, Atsushi Nakazawa, Haruo Takemura

2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) 1226 - 1233 2009

Language：English Publisher：IEEE

DOI： 10.1109/ICCV.2009.5459330

LARGE-SCALE 3D SCENE MODELING BY REGISTRATION OF LASER RANGE DATA WITH GOOGLE MAPS IMAGES Reviewed

Anuraag Agrawal, Miki Matsumura, Atsushi Nakazawa, Haruo Takemura

2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 589 - 592 2009

Language：English Publisher：IEEE

This work presents a novel approach to registering multiple range images on top of a Google Maps image. The fundamental concept behind the method is matching completely different types of input with each other using classification as a middleman. Range images and Google Maps images are separated into classes, and the range image is also projected into a 2D top-down template image. The template image can then be matched against the Google Maps image to find its location and orientation on the map, which can be used for registering the range images. An experiment comparing this technique against using GPS to find position and orientation showed that it is effective at automatically constructing a reasonable large-scale 3D model whereas GPS would be completely ineffective.

DOI： 10.1109/ICIP.2009.5413885

EYE REFLECTION ANALYSIS AND APPLICATION TO DISPLAY-CAMERA CALIBRATION Reviewed

Christian Nitschke, Atsushi Nakazawa, Haruo Takemura

2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 3449 - 3452 2009

Language：English Publisher：IEEE

We present a novel technique for calibrating display-camera systems from reflections in the user's eyes. Display-camera systems enable a range of vision applications that need controlled illumination, including 3D object reconstruction, facial modeling and human computer interaction. One important issue, though, is the geometric calibration of the display, which requires additional hardware and tedious user interaction. The proposed approach eliminates this requirement by analyzing patterns that are reflected in the cornea, a mirroring device that naturally exists in any display-camera system. By applying this strategy we also obtain a continuous estimation of eye poses which facilitates further applications. We investigate the effect of display size, camera-eye distance and individual eye anatomy experimentally using only off-the-shelf components. Results are promising and show the general feasibility of the approach.

DOI： 10.1109/ICIP.2009.5413852

Interactive 3D Video Using the Sequencing of Multiple Scenes

印象語による舞踊動作データの分類法

沼口直紀, 中澤篤志, 竹村治雄

画像電子学会年次大会予稿集(CD-ROM) 37th 2009

HATTORI Yuichi, NAKAZAWA Atsushi, TAKEMURA Haruo

The IEICE transactions on information and systems 91 ( 12 ) 2800 - 2808 2008.12

Modeling 3D Scenes with Registration between Laser Range Data and Google Maps Image

MATSUMURA Miki, AGRAWAL Anuraag, NAKAZAWA Atsushi, TAKEMURA Haruo

IEICE technical report 108 ( 328 ) 169 - 176 2008.11

Language：Japanese Publisher：The Institute of Electronics, Information and Communication Engineers

In this research, we propose a method for taking expansive 3D models of environments using highly-accurate laser range data. Laser range data is taken using distance sensors called laser range sensors, which have grown in use over recent years, including such practical applications like Google's street-view. However, trying to model a large-scale environment like a city requires taking data from various locations around the environment, and this data must be aligned with respect to each other. In our method, we initially decide on a location to model, taking range and map data for it and classifying it into multiple regions. We then find the location and orientation on the map that allows the two results to match, giving the location and orientation of the captured range data.

Modeling 3D Scenes with Registration between Laser Range Data and Google Maps Image

MATSUMURA Miki, AGRAWAL Anuraag, NAKAZAWA Atsushi, TAKEMURA Haruo

IPSJ SIG Notes. CVIM 2008 ( 115 ) 169 - 176 2008.11

Language：Japanese Publisher：Information Processing Society of Japan (IPSJ)