Faculty Profiles - Nakazawa Atsushi

MISC - Nakazawa Atsushi

Division display 121 - 140 of about 169 ／ All the affair displays >>

Report on the l0th IEEE International Conference on Computer Vision(ICCV2005)

FURUKAWA Ryo, KATO Takekazu, KAWASAKI Hiroshi, MITA Takeshi, MIYAZAKI Daisuke, NAKAZAWA Atsushi, SATO Tomokazu, SUGAYA Yasuyuki, UTSUMI Akira, SUGIMOTO Akihiro, SATO Yoichi, WADA Toshikazu

IPSJ SIG Notes. CVIM 2006 ( 25 ) 421 - 430 2006.3

D-12-69 Volume Based Motion Capture Considering Topological Difference

Tanaka Hidenori, Nakazawa Atsushi, Machida Takashi, Takemura Haruo

Proceedings of the IEICE General Conference 2006 ( 2 ) 201 - 201 2006.3

D-12-46 A Compression Method of Time Sequence Volume Data using 3D Hu Invariant Moments

Hattori Yuichi, Nakazawa Atsushi, Machida Takashi, Takemura Haruo

Proceedings of the IEICE General Conference 2006 ( 2 ) 178 - 178 2006.3

人の動きのデジタル化とその応用--モーションキャプチャと音楽情報を利用した舞踊動作の解析と生成

白鳥貴亮, 池内克史, 中澤篤志

画像ラボ 17 ( 3 ) 1 - 5 2006.3

インデックス画像を用いた複数距離画像の高速同時位置合せ

大石岳史, 中澤篤志, 池内克史

電子情報通信学会論文誌. D, 情報・システム = The IEICE transactions on information and systems / 電子情報通信学会編 89 ( 3 ) 513 - 521 2006.3

Task recognition and style analysis in dance sequences Reviewed

Manoj Perera, Takaaki Shiratori, Shunsuke Kudoh, Atsushi Nakazawa, Katsushi Ikeuchi

IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems 329 - 334 2006

Language：English

In this paper we present a novel approach to recognizing motion styles and identifying persons using the Multi Factor Tensor (MFT) model. We apply a musical information analysis method in segmenting the motion sequence relevant to the key poses and the musical rhythm. We define a task model considering the repetitive motion segment, in which motion is decomposed into task and style. Given the motion data set, we formulate the MFT model and factorize it efficiently in recognizing the tasks, the styles, and the identities of persons. In our experiments, traditional dance by several people is chosen as the motion sequence. We capture the motion data for a few cycles, segment it using the musical analysis approach, normalize the segments, and recognize a task model from them. Various experiments to evaluate the potential of the recognition ability of our proposed approach are performed, and the results demonstrate the high accuracy of our model. © 2006 IEEE.

DOI： 10.1109/MFI.2006.265645

Scopus

researchmap

観察学習パラダイムに基づく二足歩行ヒューマノイドロボットによる舞踊動作の再現 (特集:身体と運動の進化)

池内克史, 中澤篤志, 工藤俊亮

バイオメカニクス研究 10 ( 3 ) 190 - 202 2006

Synthesizing dance performance using musical and motion features Reviewed

Takaaki Shiratori, Atsushi Nakazawa, Katsushi Ikeuchi

2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10 2006 3654 - + 2006

Language：English Publisher：IEEE

This paper proposes a method for synthesizing dance performance synchronized to played music and our method presents a system that imitates dancers' skills in performing their motion while they listen to the music. Our method consists of a motion analysis, a music analysis, and a motion synthesis based on results of the analyses. In these analysis steps, motion and music features are acquired. These features are derived from motion keyframes, motion intensity, music intensity, musical beats, and chord changes. Our system also constructs a motion graph to search similar poses from given dance sequences and to connect them as possible transitions. In the synthesis step, the trajectory that provides the best correlation between music and motion features is selected from the motion graph, and the resulting motion is generated. Our experimental results indicate that our proposed method actually creates dance as the system "hears" the music.

DOI： 10.1109/ROBOT.2006.1642260

Web of Science

researchmap

Parallel Simultaneous Alignment of a Large Number of Range Images on Distributed Memory System(Image Processing)

OISHI TAKESHI, SAGAWA RYUSUKE, NAKAZAWA ATSUSHI, KURAZUME RYO, IKEUCHI KATSUSHI

IPSJ Journal 46 ( 9 ) 2369 - 2378 2005.9

Language：Japanese Publisher：一般社団法人情報処理学会

CiNii Article

researchmap

Parallel Simultaneous Alignment of a Large Number of Range Images on Distributed Memory System

OISHI TAKESHI, SAGAWA RYUSUKE, NAKAZAWA ATSUSHI, KURAZUME RYO, IKEUCHI KATSUSHI

IPSJ journal 46 ( 9 ) 2369 - 2378 2005.9

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

This paper describes a method for parallel alignment of multiple range images. Since it is difficult to align a large number of range images simultaneously, we developed a parallel method to accelerate and reduce the memory requirement of the process. Although a general simultaneous alignment algorithm searches correspondences for all pairs of all range images, by rejecting redundant dependencies, our method makes it possible to accelerate computation time and reduce the amount of memory used on each node. The correspondence search is performed independently for each pair of range images. Accordingly, the computations between the pairs are preformed in parallel on multiple processors. All relations between range images are described as a pair node hyper-graph. Then, an optimal pair assignment is computed by partitioning the graph properly. The method was tested on a 16 processor PC cluster, where it demonstrated the high extendibility and the performance improvement in time and memory.

CiNii Article

CiNii Books

researchmap

Other Link： http://id.nii.ac.jp/1001/00010541/

The Structure Analysis of Dance Motions Using Motion Capture and Musical Information

SHIRATORI Takaaki, NAKAZAWA Atsushi, IKEUCHI Katsushi

The transactions of the Institute of Electronics, Information and Communication Engineers. D-II 88 ( 8 ) 1662 - 1671 2005.8

Extraction of Natural Quadric Surfaces from Range Image Using Hough Transform and EM Algorithm

YAMAMOTO Kokushi, NAKAZAWA Atsushi, KIYOKAWA Kiyoshi, TAKEMURA Haruo

IEICE technical report. Natural language understanding and models of communication 104 ( 667 ) 55 - 60 2005.2

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

In this paper, we present a novel method to estimate several natural quadric (sphere, cylinder, and cone) and plane surface parameters from a range image. First, model surface parameters are estimated using Hough transform technique. Based on these estimated parameters, more reliable parameters are calculated using the EM algorithm. We implemented this method and applied to actual range data.

CiNii Article

CiNii Books

researchmap

観察に基づく音楽およびモーションキャプチャデータからの舞踊動作生成手法

中澤篤志

第22回画像の認識理解シンポジウム (MIRU2005), August 2005

Fast simultaneous alignment of multiple range images using index images Reviewed

T Oishi, A Nakazawa, R Kurazume, K Ikeuchi

FIFTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS 476 - 483 2005

Language：English Publisher：IEEE COMPUTER SOC

This paper describes a fast and easy-to-use simultaneous alignment method of multiple range images. The most time consuming part of alignment process is searching corresponding points. Although "Inverse calibration" method quickly searches corresponding points in complexity O(n), where n is the number of vertices, the method requires some look-up tables or precise sensor parameters. Then, we propose an easy-to-use method that uses "Index Image": "Index image" can be rapidly created using graphics hardware without precise sensor parameters. For fast computation of rigid transformation matrices of a large number of range images, we utilized linearized error function and applied incomplete Cholesky conjugate gradient (ICCG) method for solving linear equations. Some experimental results that aligned a large number of range images measured with laser range sensors show the effectiveness of our method.

DOI： 10.1109/3DIM.2005.41

Web of Science

researchmap

Task model of lower body motion for a biped humanoid robot to imitate human dances Reviewed

S Nakaoka, A Nakazawa, F Kanehiro, K Kaneko, M Morisawa, K Ikeuchi

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vols 1-4 2769 - 2774 2005

Language：English Publisher：IEEE

The goal of this study is developing a biped humanoid robot that can observe a human dance performance and imitate it. To achieve this goal, we propose a task model of lower body motion, which consists of task primitives (what to do) and skill parameters (how to do it). Based on this model, a sequence of task primitives and their skill parameters are detected from human motion, and robot motion is regenerated from the detected result under constraints of a robot. This model can generate human-like lower body motion including various waist motions as well as various stepping motions of the legs. Generated motions can be performed stably oil an actual robot supported by its own legs. We used improved robot hardware HRP-2, which has superior features in body weight, actuators, and DOF of the waist. By using the proposed method and HRP-2, we have realized a dance performance of Japanese folk dance by the robot, which is synchronized with a performance of a human grand master on the same stage.

DOI： 10.1109/IROS.2005.1545395

Web of Science

researchmap

語学教育教材を利用した大学合同による実証実験 Reviewed

間瀬健二, 梶田将司, Seiie Jang, 上田真由美, 杉浦達樹, 佐々木順子, 美濃導彦, 壇辻正剛, 中村裕一, 角所考, 元木環, 正司哲朗, 竹村治雄, 中澤篤志, 浦真吾, 鐘ヶ江力, 岩澤亮祐

文部科学省研究委託事業『知的資産の電子的な保存・活用を支援するソフトウェア技術基盤の構築』平成17 年度研究概要, pp. 27–34, 2005-12. 2005

大阪大学サイバーメディアセンターにおける新情報教育システム

桝田秀夫, 小川剛史, 中澤篤志, 町田貴史, 清川清, 竹村治雄

PC Conference論文集 2005 (Web) 2005

ユビキタス環境下での次世代コース管理システム

梶田将司, 中澤篤志, 角所考

名古屋大学情報連携基盤センターニュース 3 ( 4 ) 271 - 276 2004.11

Structure Analysis of Human Motion and Motion Imitation of Humanoids -Dancing Humanoid Project-

NAKAZAWA Atsushi, NAKAOKA Shinichiro, SHIRATORI Takaaki, KUDOH Shunsuke, IKEUCHI Katsushi

IPSJ SIG Notes. CVIM 2004 ( 113 ) 31 - 39 2004.11

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

The interaction of robots is the reaction to their outer world according to the outer signals made by humans or environments. In particular, the humanoids which do the cooperative tasks with humans have to be considered how smoothly and naturally communicate with humans. This is achieved by the technologies of the natural motion synthesis or understanding of outer signals. In this paper, we introduce our project which aims to develop the methods to import human motion into humanoids, in particular, human dance motion. Through our research, we concentrated that how to express the 'naturality' of human and synchronization method to the important signals of dances: music signals.

CiNii Article

CiNii Books

researchmap

Other Link： http://id.nii.ac.jp/1001/00052434/

民俗芸能のデジタルアーカイブとロボットによる動作提示

池内克史, 中澤篤志, 小川原光一, 高松淳, 工藤俊亮, 中岡慎一郎, 白鳥貴亮

日本バーチャルリアリティ学会誌 = Journal of the Virtual Reality Society of Japan 9 ( 2 ) 78 - 84 2004.6

　 PREV - NEXT 　

< Nakazawa Atsushi >

MISC - Nakazawa Atsushi