|Workshop proposals : Feb 25, 2014
|Paper submission :
|Mar 1, 2014 → Mar 31, 2014
|Paper acceptance :
|Mar 30, 2014 → June 4, 2014
|Camera ready : June 22, 2014
|Early registration :June 22, 2014
|Conference : Aug 26-29
HOME | AVSS2014 | Keynote Lectures
|Title : Video Analysis of Human Body (August 27) |
|Takeo Kanade, Professor, Robotics Institute and Computer
Science, Carnegie Mellon University |
|Detailed analysis of a human body in video, especially precise alignment of body parts, is a key technology for advanced surveillance that requires genuine understanding of people’s behavior. The problem is far more difficult than whole-body detection and tracking because it has to deal with the high degree of freedom and self occlusion. This talk will discuss some recent progress in this important topic, and suggest further research. |
Kanade is the U. A. and Helen Whitaker University Professor of Computer
Science and Robotics and the director of Quality of Life Technology Engineering
Research Center at Carnegie Mellon University. He received his Doctoral
degree in Electrical Engineering from Kyoto University, Japan, in 1974.
After holding a faculty position in the Department of Information Science,
Kyoto University, he joined Carnegie Mellon University in 1980. He was
the Director of the Robotics Institute from 1992 to 2001. He also founded
the Digital Human Research Center in Tokyo and served as the founding
director from 2001 to 2010.
Dr. Kanade works in multiple areas of robotics: computer vision, multi-media,
manipulators, autonomous mobile robots, medical robotics and sensors.
He has written more than 400 technical papers and reports in these areas,
and holds more than 20 patents. He has been the principal investigator
of more than a dozen major vision and robotics projects at Carnegie Mellon.
Dr. Kanade has been elected to the National Academy of Engineering and
the American Academy of Arts and Sciences. He is a Fellow of the IEEE,
a Fellow of the ACM, a Founding Fellow of American Association of Artificial
Intelligence (AAAI), and the former and founding editor of International
Journal of Computer Vision. Awards he received includes the Franklin Institute
Bower Prize, ACM/AAAI Newell Award, Okawa Award, C&C Award, Tateishi
Grand Prize, Joseph Engelberger Award, IEEE Robotics and Automation Society
Pioneer Award, FIT Accomplishment Award, and IEEE PAMI-TC Azriel Rosenfeld
Lifetime Accomplishment Award.
|Title : Riemannian Manifolds, Kernels and Learning (August
|Richard Hartley, Professor, Australian National University |
|I will talk about recent results from a number of people in my group on
Riemannian manifolds in computer vision. In many Vision problems Riemannian
manifolds come up as a natural model. Data related to a problem can be naturally
represented as a point on a Riemannian manifold. This talk will give an
intuitive introduction to Riemannian manifolds, and show how they can be
applied in many situations. |
Manifolds of interest include the manifold of Positive Definite matrices
and the Grassman Manifolds, which have a role in object recognition and
classification, and the Kendall shape manifold, which represents the shape
of 2D objects. Of particular interest is the question of when one can define
positive- definite kernels on Riemannian manifolds. This would allow the
application of kernel techniques of SVMs, Kernel FDA, dictionary learning
etc directly on the manifold.
University of Toronto, Canada PhD Mathematics, 1976, MSc 1972
Stanford University, MSc Computer Science, 1985
Australian National University, BSc, 1971"
Richard Hartley is head of the computer vision group in the Department
of Information Engineering, at the Australian National University, where
he has been since January, 2001. He also co-leader of the Computer Vision
group in NICTA, a research laboratory set up in 2002 with funding from
the Australian Government.
Dr. Hartley worked at the General Electric Research and Development Center
from 1985 to 2001. During the period 1985-1988, he was involved in the
design and implementation of Computer-Aided Design tools for electronic
design and created a very successful design system called the Parsifal
Silicon Compiler. In 1991 he was awarded GE's Dushman Award for this work.
He became involved with Image Understanding and Scene Reconstruction working
with GE's Simulation and Control Systems Division. He worked on several
Imaging projects, including medical imaging, document imaging and visual
inspection. In 1991, he began an extended research effort in the area
of applying projective geometry techniques to reconstruction. This research
direction was one of the dominant themes in computer vision research throughout
the 1990s. In 2000, he co-authored (with Andrew Zisserman) a book for
Cambridge University Press, summarizing the previous decade’s research
in this area.
|Title : Intelligent Transport Systems (ITS)
for Next Generation with Advanced Surveillance (August 29) |
|Young-Jun MOON, Ph.D., Director, The Korea Transport Institute
|The study proposes the initiative plan for technical and political approaches on the intelligent transport systems (ITS) for the next generation cooperated with connected vehicles including advanced surveillance and information and communication technologies (ICT). |
The utilization of scientific methodologies enables us to design and construct bridges, roads, buildings, ships, aircraft, automobiles, and other mechanical wonders. Recently, the most people may understand the scientific way when it comes to airplane rides or building things like highway, bridges, and vehicles. Now it's time to develop a consensus that when it comes to planning our societies: our cities, transportation systems, social infrastructure, and so on.
This study issues the needs for a new paradigm of transportation systems to design the future, Cooperative Intelligent Transport Systems (C-ITS) with fully networked vehicle transportation systems, where computer guided vehicles for land, sea, air, space and beyond can transport passengers and freight in and between the new cities. In order to prepare for our future by thinking and leaning utilizing the present methodologies and values in the transportation world, the advanced surveillance technology initiatives proposed in this study will be discussed to generate the succeeding issues for future research and development in the world impacting on cooperative and sustainable transport systems for human life and the industry that penetrate the global markets.
Young-Jun MOON is a director of Division for Innovative Transportation
Technology Convergence in the Korea Transport Institute (KOTI). He has
joined KOTI in 1998, right after he had graduated in the Univ. of Illinois
at Urbana-Champaign (UIUC) with a doctoral degree of Transportation Engineering
in the Dept. of Civil and Environmental Engineering.
He started his career as a research engineer in the Agency for Defense
Development (ADD) in 1987, developing Korean Surface to Air Missile (KSAM)
for the military weapon systems. He participated in ITS World Congress
and the International Standard Organizations in ITS area as a leader of
ITS R&D in Korea from 1999 for developing a variety of ITS projects.
Since then, he has been involved in ISO/TC204 as not only an expert in
WG14 vehicle/roadway warning and control system but also a Convenor of
WG for nomadic & portable devices. He has been a member of the International
Program Committee of ITS World Congress since 2005 and also a chair of
IPC for the 17th ITS World Congress in Busan, 2010.
He became a member of National Science and Technology Commission (NSTC)
under the President House in 2010, and a chair of Construction & Transportation
Committee. He is also a chair of Transportation Division in PyeongChang
2018 Olympic and Paralympic Winter Games Organizing Committee since 2010.