Katsushi IKEUCHI Ph.D

Sr. Principal Research Manager, Applied Robotics Research, Microsoft Corporation

katsuike@microsoft.com

Emeritus Professor, University of Tokyo

katsushi.ikeuchi@outlook.jp

ki@cvl.iis.u-tokyo.ac.jp

Biography

Education:

· B Eng degree in Mechanical Engineering from Kyoto University in 1973

· M Eng degree in Information Engineering from the University of Tokyo in 1975

· Ph D degree in Information Engineering from the University of Tokyo in 1978.

After working at

· Artificial Intelligence Laboratory, Massachusetts Institute of Technology for three years,

· Electrotechnical Laboratory, Ministry of International Trade and Industry, Japanese Government for five years,

· Robotics Institute, Carnegie Mellon University for ten years, and

· Institute of Industrial Science, University of Tokyo for nineteen years,

he joined Microsoft Research in 2015. During this tenure, he supervised more than fifty PhD students.

His community service includes:

· general chair of IROS95, ITSC99, MVA00, IV01, ICCV05, ACCV07

· program chair of CVPR96, MVA98, IV02, ICCV03, ICRA09, ICPR12, ICCV15

· associate editor of IEEE Trans. RA, IEEE Trans. PAMI

· a distinguished lecturer of IEEE Signal Processing Society in 2000-2002, IEEE Computer Society in 2004-2006 and Robotics and Automation Society in 2009-2010, and

· the editor-in-chief of the International Journal of Computer Vision.

· IEEE Robotics and Automation Society Adcom (1998-2004, 2006-2008), IEEE ITS Society BOG (2008-2012), IEEE Fellow Committee (2010-2012), 2^nd VP of International Association of Pattern Recognition (2006-2008).

Through these research and society service, he was awarded a fellow from IEEE, IEICE, IPSJ and RSJ.

His research activities span computer vision, computer graphics, robotics, and intelligent transportation systems. In these research fields, he has received a dozen or so best paper awards, including

· David Marr Prize in computational vision for the paper “Shape from Interreflection”,

· IEEE Robotics and Automation Society K. S. Fu memorial best transaction paper award for the paper “Toward Automatic Robot Instruction from Perception-Mapping Human Grasps to Manipulator Grasps”.

· In addition, in 1992, his paper “Numerical Shape from Shading and Occluding Boundaries” was selected as one of the most influential papers to have appeared in the Artificial Intelligence Journal within the past 10 years.

He is the winner of

· Distinguished Researcher Award from IEEE-PAMI, 

· Medal of Honor with Purple Ribbon (Shiju-ho-syo) from Japanese Emperor

· the Okawa award from Okawa foundation,

· Funai Award from IPSJ.

Representative Publications

Computer Vision

• Numerical Shape From Shading and Occluding Boundaries: AIJ, 17(1-3): 141-184, 1981
  --- The original paper to the smoothness constraint in the computer vision community
• Automatic Generation of Object Recognition Program: Proc of the IEEE, 76(8): 1016-1035, 1988
  --- The VAC really generates a program!!!
• A Spherical Representation for the Recognition of Free-Form Surfaces: IEEE Trans. PAMI, 17(7): 681-690, 1995
  --- The final destination of spherical representations
• Object shape and reflectance modeling from observation: SIGGRAPH 97, pp 379-387, 1997
  --- Beginning of image-based modeling
• Acquiring a radiance distribution to superimpose virtual objects onto a real scene: IEEE Trans. VCG, 5(1):1-12, 1999
  --- Generating soft shadow around an object for mix reality applications
• Eigen-Texture Method: Appearance Compression and Synthesis based on 3D Model: IEEE Trans. PAMI, 23(11): 1257-1265, 2001
  --- Storing texture on object surface
• (Book) Computer Vision – a reference guide, Springer 2014

Robotics

• The Mechanical Manipulation of Randomly Oriented Parts: Scientific American, 251(2): 100-111, 1984
  --- It's fun to pick up a doughnut (doughnut picking demo with example-based photometric stereo and extended Gaussian image) (lookup-table-generation for example-based photometric stereo)
• Toward an Assembly Plan from Observation Part I: Task Recognition with Polyhedral Objects: IEEE Trans. R&A, 10(3): 368-385, 1994
  --- For our beautiful co-operations among Robots and Humans (two-block demo (narration)) (polyhedral objects with error correction demo)
• Toward Automatic Robot Instruction from Perception-Mapping Human Grasps to Manipulator Grasps: IEEE Trans. RO 13(1): 81-95, 1997
  --- For our beautiful co-operations among Robots and Humans
• Representation for Knot-tying Tasks: IEEE Trans. RO, 22(1): 65-78, 2006
  --- We can handle knot typing based on learning-from-observation paradigm
• Learning from observation paradigm: Leg Task Models for Enabling a Biped Humanoid Robot to Imitate Human Dance: IJRR, 26(8): 829-844, 2007
  --- Bandaisan dance demo by a HRP-2 with the dance teacher
• Toward a Dancing Robot with Listening Capability: Keypose-based Integreation of Lower-, Middle-, and Upper-Body Motions for Varying Music Tempos: IEEE Trans RO, 30(3): 771-778, 2014
  --- Donpan dance demo with varying motion speed

e-Heritage

• The Great Buddha Project: Digitally Archiving, Restoring and Analyzing Cultural Heritage Objects, IJCV 71(1): 189-208, 2007
  --- The great Buddha project (movie on overview (narration))
• Flying Laser Range Sensor for Large-Scale Site-Modeling and Its Applications in Bayon Digital Archival Project: IJCV 78(2-3): 207-222, 2008
  --- The digital Bayon project (movie on sensing (narration)) (resulting 3D Bayon)
• (book) Digitally archiving cultural objects, Springer, 2008
  --- a collection of papers developed in digital Bayon project
• (book) Kyushu painted tumuli, Tokyo shoseki, 2014 (in Japanese)
  --- twenty painted tumuli have been digitized and a dozen new findings in archaeology have been discovered

Representative Talks

• e-Heritage Project(mp4 movie based on slide+video)
  --- Digital Bayon and Cyber Archaeology given at AAAS2015
• e-Intangible heritage
  --- Dancing robot and labanotation