Faculty Profiles - OGAWARA Koichi

Published Papers - OGAWARA Koichi

Division display21 - 40 of about 58／ All the affair displays >>

相互制約付き多数決型アルゴリズムによる時系列パターン認識

福冨正弘, 小川原光一, 馮尭楷, 内田誠一

電子情報通信学会論文誌 J93-D ( 4 ) 548 - 551 2010.04 [Refereed]

Detecting Repeated Patterns using Partly Locality Sensitive Hashing

Koichi Ogawara, Yasufumi Tanabe, Ryo Kurazume, Tsutomu Hasegawa

IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010) ( IEEE ) 2010 [Refereed]

Repeated patterns are useful clues to learn previously unknown events in an unsupervised way. This paper presents a novel method that detects relatively long variable-length unknown repeated patterns in a motion sequence efficiently.
The major contribution of the paper is two-fold: (1) Partly Locality Sensitive Hashing (PLSH) [1] is employed to find repeated patterns efficiently and (2) the problem of finding consecutive time frames that have a large number of repeated patterns is formulated as a combinatorial optimization problem which is solved via Dynamic Programming (DP) in polynomial time O( N1+1/alpha) thanks to PLSH where N is the total amount of data. The proposed method was evaluated by detecting repeated interactions between objects in everyday manipulation tasks and outperformed previous methods in terms of accuracy or computational time.

Approximate belief propagation by hierarchical averaging of outgoing messages

Koichi Ogawara

Proceedings - International Conference on Pattern Recognition 1368 - 1372 2010 [Refereed]

This paper presents an approximate belief propagation algorithm that replaces outgoing messages from a node with the averaged outgoing message and propagates messages from a low resolution graph to the original graph hierarchically. The proposed method reduces the computational time by half or two-thirds and reduces the required amount of memory by 60% compared with the standard belief propagation algorithm when applied to an image. The proposed method was implemented on CPU and GPU, and was evaluated against Middlebury stereo benchmark dataset in comparison with the standard belief propagation algorithm. It is shown that the proposed method outperforms the other in terms of both the computational time and the required amount of memory with minor loss of accuracy. © 2010 IEEE.

DOI

Painting robot with multi-fingered hands and stereo vision.

Shunsuke Kudoh, Koichi Ogawara, Miti Ruchanurucks, Katsushi Ikeuchi

Robotics Auton. Syst. 57 ( 3 ) 279 - 288 2009.03 [Refereed]

DOI

Detecting Repeated Motion Patterns via Dynamic Programming using Motion Density

Koichi Ogawara, Yasufumi Tanabe, Ryo Kurazume, Tsutomu Hasegawa

ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7 ( IEEE ) 2926 - + 2009 [Refereed]

In this paper, we propose a method that detects repeated motion patterns in a long motion sequence efficiently. Repeated motion patterns are the structured information that can be obtained without knowledge of the context of motions. They can be used as a seed to find causal relationships between motions or to obtain contextual information of human activity, which is useful for intelligent systems that support human activity in everyday environment.
The major contribution of the proposed method is two-fold:
(1) motion density is proposed as a repeatability measure and
(2) the problem of finding consecutive time frames with large motion density is formulated as a combinatorial optimization problem which is solved via Dynamic Programming (DP) in polynomial time O(N log N) where N is the total amount of data. The proposed method was evaluated by detecting repeated interactions between objects in everyday manipulation tasks and outperformed the previous method in terms of both detectability and computational time.

Integrating Region Growing and Classification for Segmentation and Matting

Miti Ruchanurucks, Koichi Ogawara, Katsushi Ikeuchi

2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5 ( IEEE ) 593 - 596 2008 [Refereed]

This paper presents a supervised foreground segmentation method that uses local and global feature similarity with edge constraint. This framework integrates and extends the notion of region growing and classification to deal with local and global fitness. It parameterizes constraint of growing using Chebyshev's inequality. The constraint is used to stop segmentation before matting. Matting relies on both local and global information. The proposed method outperforms many of the current methods in the sense of correctness and minimal user interaction, and it does so in a reasonable computation time.

Learning Meaningful Interactions from Repetitious Motion Patterns

Koichi Ogawara, Yasufumi Tanabe, Ryo Kurazume, Tsutomu Hasegawa

2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS ( IEEE ) 3350 - + 2008 [Refereed]

In this paper, we propose a method for estimating meaningful actions from long-term observation of everyday manipulation tasks without prior knowledge as part of an action understanding framework for life support robotic systems. The target task is defined as a sequence of interactions between objects. An interaction that appears many times is assumed to be meaningful and repetitious relative motion patterns are detected from trajectories of multiple objects. The main contribution is that the problem is formulated as a combinatorial optimization problem with two parameters, target object labels and correspondences on similar motion patterns, and is solved using local and global Dynamic Programming (DP) in polynomial time O(N log N), where N is a total amount of data. The proposed method is evaluated against manipulation tasks using everyday objects such as a cup and a tea-pot.

DOI

Representation of Drawing Behavior by a Robot

KUDOH Shunsuke, OGAWARA Koichi, RUCHANURUCKS Miti, TAKAMATSU Jun, IKEUCHI Katsushi

Journal of the Robotics Society of Japan ( The Robotics Society of Japan ) 26 ( 6 ) 612 - 619 2008 [Refereed]

This paper describes a painting robot with multi-fingered hands and stereo vision. The goal of this study is for the robot to reproduce the whole procedure involved in human painting. A painting action is divided into three phases: obtaining a 3D model, composing a picture model, and painting by a robot. In this system, various feedback techniques including computer vision and force sensors are used. As experiments, an apple and a human silhouette are painted on a canvas using this system.

DOI

Integrating Region Growing and Classification for Segmentation and Matting

Miti Ruchanurucks, Koichi Ogawara, Katsushi Ikeuchi

2008 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS ( IEEE ) 597 - + 2008 [Refereed]

This paper presents a supervised foreground segmentation method that uses local and global feature similarity with edge constraint. This framework integrates and extends the notion of region growing and classification to deal with local anti global fitness. It parameterizes constraint of growing using Chebyshev's inequality. The constraint is used to stop segmentation before matting. Matting relies on both local and global information. The proposed method outperform many of the current methods in the sense of correctness and minimal user interaction, and it does so in a reasonable computation time.

Condtruction method of drift-free omni images by integration of multiple video cameras

MIKAMI Takeshi, ONO Shintaro, OGAWARA Koichi, KAWASAKI Hiroshi, IKEUCHI Katsushi

Monthly journal of the Institute of Industrial Science, University of Tokyo ( The University of Tokyo ) 59 ( 3 ) 80 - 84 2007.05

DOI

Marker-less human motion estimation using articulated deformable model

Koichi Ogawara, Xiaolu Li, Katsushi Ikeuchi

PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10 ( IEEE ) 46 - 51 2007 [Refereed]

This paper presents a novel whole body motion estimation method by fitting a deformable articulated model of the human body into the 31) reconstructed volume obtained from multiple video streams. The advantage of the proposed method is two fold: (1) combination of a robust estimator and ICP algorithm with Kd-tree search in pose and normal space make it possible to track complex and dynamic motion robustly against noise and interference between limb and torso, (2) the hierarchical estimation and backtrack re-estimation algorithm enable accurate estimation.
The power to track challenging whole body motion in real environment is also presented.

Robot painter: From object to trajectory

Miti Ruchanurucks, Shunsuke Kudoh, Koichi Ogawara, Takaaki Shiratori, Katsushi Ikeuchi

2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9 ( IEEE ) 345 - + 2007 [Refereed]

This paper presents visual perception discovered in high-level manipulator planning for a robot to reproduce the procedure involved in human painting. First, we propose a technique of 3D object segmentation that can work well even when the precision of the cameras is inadequate. Second, we apply a simple yet powerful fast color perception model that shows similarity to human perception. The method outperforms many existing interactive color perception algorithms. Third, we generate global orientation map perception using a radial basis function. Finally, we use the derived foreground, color segments, and orientation map to produce a visual feedback drawing. Our main contributions are 3D object segmentation and color perception schemes.

Humanoid robot painter: Visual perception and high-level manning

Miti Ruchanurucks, Shunsuke Kudoh, Koichi Ogawara, Takaaki Shiratori, Katsushi Ikeuchi

PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10 ( IEEE ) 3028 - + 2007 [Refereed]

This paper presents visual perception discovered in high-level manipulator planning for a robot to reproduce the procedure involved in human painting. First, we apply a technique of 2D object segmentation that considers region similarity as an objective function and edge as a constraint with artificial intelligent used as a criterion function. The system can segment images more effectively than most of existing methods, even if the foreground is very similar to the background. Second, we propose a novel color perception model that shows similarity to human perception. The method outperforms many existing color reduction algorithms. Third, we propose a novel global orientation map perception using a radial basis function. Finally, we use the derived model along with the brush's position- and force-sensing to produce a visual feedback drawing. Experiments show that our system can generate good paintings including portraits.

Recognizing Assembly Tasks Through Human Demonstration.

Jun Takamatsu, Koichi Ogawara, Hiroshi Kimura, Katsushi Ikeuchi

International Journal of Robotics Research 26 ( 7 ) 641 - 659 2007 [Refereed]

DOI

Representation for knot-tying tasks.

Jun Takamatsu, Takuma Morita, Koichi Ogawara, Hiroshi Kimura, Katsushi Ikeuchi

IEEE Transactions on Robotics 22 ( 1 ) 65 - 78 2006 [Refereed]

DOI

Painting robot with multi-fingered hands and stereo vision

Shunsuke Kudoh, Koichi Ogawara, Miti Ruchanurucks, Katsushi Ikeuchi

IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems 127 - 132 2006 [Refereed]

In this paper, we describe a painting robot with multi-fingered hands and stereo vision. The goal of this study is for the robot to reproduce the whole procedure involved in human painting. A painting action is divided into three phases: obtaining a 3D model, composing a picture model, and painting by a robot. In this system, various feedback techniques including computer vision and force sensors are used. As experiments, an apple and a human silhouette are painted on a canvas using this system. © 2006 IEEE.

DOI

Laser Range Sensor Suspended beneath Balloon : FLRS (Flying Laser Range Sensor)

HASEGAWA Kazuhide, HIROTA Yuichiro, OGAWARA Koichi, KURAZUME Ryo, IKEUCHI Katsushi

The transactions of the Institute of Electronics, Information and Communication Engineers. D-II ( The Institute of Electronics, Information and Communication Engineers ) J88-D-II ( 8 ) 1499 - 1507 2005.08 [Refereed]

レーザレンジセンサなどを用いた計測作業において, 遺跡や建物などの対象物が大規模になればなるほど, 地上からは観測できないオクルージョン領域が発生する. 一般的には足場を組んでセンサを持ち上げてその上部からの計測を行っているが, 計測位置の移動には多くの時間とコストがかかる. また, 足場を組むことが不可能な場合は計測作業自体が止まることにもなる. この問題を解決するために, 筆者らは気球を用いて空中から計測を行うことにより, 足場を組むことなく手軽に計測位置の移動を可能にするレーザレンジセンサFLRSの開発を行った. このセンサでは, 気球の揺れによる影響を少なくするために高速な計測を実現しているが, 計測結果には若干のひずみが発生している. そこで, センサに内蔵しているビデオカメラからの連続画像を用いて, センサ本体の動きを検出して補正する手法を提案する. そして, 実際に遺跡計測に用いた例を挙げ, センサシステムの有効性を示す.

Representation of Knot Tying Tasks for Robot Execution

TAKAMATSU Jun, MORITA Takuma, OGAWARA Koichi, KIMURA Hiroshi, IKEUCHI Katsushi

Journal of the Robotics Society of Japan ( The Robotics Society of Japan ) 23 ( 5 ) 572 - 582 2005.07 [Refereed]

The<I>Learning from Observation</I> (LFO) paradigm has been widely applied in various types of robot systems. It helps reduce the work of the programmer. However, so far, the available systems have application limited to rigid objects. Deformable objects are not considered, because: (1) it is difficult to describe their states and (2) too many operations are possible on them. In this paper, we choose knot-tying tasks as case study for operating on deformable objects, since the<I>knot theory</I>is available and since types of operations are limited. In actuality, we introduce an appropriate representation for describing knot's states and define four types of operations enough to realize any knot-tying tasks.

DOI

ロボット動作の自動生成のための観察による組み立て作業の抽象化

高松淳, 小川原光一, 木村浩, 池内克史

情報処理学会論文誌コンピュータビジョンとイメージメディア 46 ( SIG 9 ) 41 - 55 2005.06 [Refereed]

A sensor fusion approach for recognizing continuous human grasping sequences using hidden Markov models

Keni Bernardin, Koichi Ogawara, Katsushi Ikeuchi, Ruediger Dillmann

IEEE Transactions on Robotics 21 ( 1 ) 47 - 57 2005.02 [Refereed]

The Programming by Demonstration (PbD) technique aims at teaching a robot to accomplish a task by learning from a human demonstration. In a manipulation context, recognizing the demonstrator's hand gestures, specifically when and how objects are grasped, plays a significant role. Here, a system is presented that uses both hand shape and contact-point information obtained from a data glove and tactile sensors to recognize continuous human-grasp sequences. The sensor fusion, grasp classification, and task segmentation are made by a hidden Markov model recognizer. Twelve different grasp types from a general, task-independent taxonomy are recognized. An accuracy of up to 95% could be achieved for a multiple-user system. © 2005 IEEE.

DOI

　 PREV - NEXT 　

<OGAWARA Koichi>

Published Papers - OGAWARA Koichi