Presenter: Anthony Hoogs (Homepage)

Event Dates:
  Tuesday April 22, 2014 from 2:00pm to 3:00pm

* Alternate Location: Towne 337*

The scale of video data continues to grow exponentially, including city-scale wide-area aerial video showing hundreds or thousands of simultaneous movers. Extracting the most interesting, salient content from this type of video is of increasing importance as the data volume grows while the vast majority of events are not of interest. However, traditional methods often fail because of low resolution and low frame rates in this domain.

Presenter's Biography:

Dr. Anthony Hoogs is the Senior Director of Computer Vision at Kitware, a small software R&D firm based on open source. Dr. Hoogs joined Kitware in August 2007 and founded the Computer Vision group, which now has 25 members including 12 PhDs. He has initiated and led more than two dozen contracts in video and motion analysis, involving more than 15 universities including the University of Pennsylvania. At GE Global Research (1998-2007), Dr. Hoogs led a team of researchers in video and imagery analysis on projects sponsored by the US Government, Lockheed Martin and NBC Universal. For more than two decades, he has supervised and performed research in various areas of computer vision including: event, activity and behavior recognition; motion pattern learning and anomaly detection; tracking; visual semantics; image segmentation; object recognition; and content-based retrieval. He has published more than 70 papers in computer vision, has served as Workshops Chair, Corporate Relations Chair and Area Chair for CVPR, and is on the steering committee for the Winter conference on Applications of Computer Vision (WACV). Dr. Hoogs received a Ph.D. in Computer and Information Science from the University of Pennsylvania in 1998, in the GRASP Lab under Dr. Ruzena Bajcsy; an M.S. from the University of Illinois at Urbana-Champaign in 1991; and a B.A. from Amherst College in 1989.

Wednesday April 2, 2014

"Meet Dr. Robot" in Drive the District

Presenter: Masaki Ogura (Homepage)

Event Dates:
  Monday April 7, 2014 from 2:00pm to 3:00pm

* Alternate Location: Levine 307*

The talk presents my recent research on the stability analysis of switched systems, which are a class of dynamical systems whose dynamics can abruptly change. Examples include the control of systems over unreliable networks or with a failure-prone controller. In this talk I will discuss a fundamental property called stability of switched linear systems. I will in particular focus on the case when switching is modeled by non-traditional stochastic processes, in particular, by non-Markovian processes.


Presenter's Biography:

Masaki Ogura is a Ph.D. candidate in applied mathematics at Texas Tech University. His primary research area is systems and control theory and his research interests include switching systems, infinite-dimensional systems, and signal processing. He is presently working on an application of switching systems to reliability theory. He obtained his Master's degree in Informatics from Kyoto University, Japan, in 2009.

Presenter: Hyun Soo Park (Homepage)

Event Dates:
  Friday March 14, 2014 from 1:30pm to 2:30pm

* Alternate Location: Levine 512*

A social camera is a camera carried or worn by a member of a social group, (e.g., a smartphone camera, a hand-held camcorder, or a wearable camera). These cameras are becoming increasingly immersed in our social lives and closely capture our social activities. In this talk, I argue that social cameras are the ideal sensors for social scene understanding, as they inherit social signals such as the gaze behavior of the people carrying them. I will present a computational representation for social scene understanding from social cameras. 


Presenter's Biography:

Hyun Soo Park is a Ph.D. student in Mechanical Engineering at Carnegie Mellon University under the supervision of Prof. Yaser Sheikh. He is interested in computer vision, graphics, and robotics. The main focus of his research is developing a computational basis for social scene understanding. He interned at Disney Research, Pittsburgh (2011) and Mircosoft Research, Redmond (2013). He received his bachelor’s degree from POSTECH, Korea in 2007, and master’s degree from Carnegie Mellon University in 2009.

Presenter: Marty Golubitsky (Homepage)

Event Dates:
  Friday March 28, 2014 from 2:00pm to 3:00pm

* Alternate Location: Towne 337*

This talk will discuss previous work on quadrupedal gaits and recent work on a generalized model for binocular rivalry proposed by Hugh Wilson. Both applications show how rigid phase-shift synchrony in periodic solutions of coupled systems of differential equations can help understand high level collective behavior in the nervous system.  For gaits the symmetries predict unexpected gaits and for binocular rivalry the symmetries predict unexpected percepts.


Presenter's Biography:

Martin Golubitsky is Distinguished Professor of Natural and Mathematical Sciences at the Ohio State University, where he serves as Director of the Mathematical Biosciences Institute. He received his PhD in Mathematics from M.I.T. in 1970 and has been Professor of Mathematics at Arizona State University (1979-83) and Cullen Distinguished Professor of Mathematics at the University of Houston (1983-2008). Dr. Golubitsky works in the fields of nonlinear dynamics and bifurcation theory studying the role of symmetry in the formation of patterns in physical systems and the role of network architecture in the dynamics of coupled systems. His recent research focuses on some mathematical aspects of biological applications: animal gaits, the visual cortex, the auditory system, and coupled systems. Dr. Golubitsky is a Fellow of the American Academy of Arts and Sciences, the American Association for the Advancement of Science (AAAS), the American Mathematical Society (AMS), and the Society for Industrial and Applied Mathematics (SIAM). He is also the 1997 recipient of the University of Houston Esther Farfel Award, the 2001 corecipient of the Ferran Sunyer i Balaguer Prize (for The Symmetry Perspective) and the recipient of the 2009 Moser Lecture Prize of the SIAM Dynamical Systems Activity Group. Dr. Golubitsky was the founding Editor-in-Chief of the SIAM Journal on Applied Dynamical Systems and has served as President of SIAM (2005-06).

Monday January 27, 2014

REPURPOSING ROBOTICS
Yolanda Chen/News Photo Editor
Monday night kicked

Monday February 10, 2014

Love robots and kids! GRASP is looking for two outstanding candidates interested in spending a year fighting poverty in Philadelphia with robots!

Thursday February 6, 2014

LEGO robotics tournament returns to Penn

LEGO story

Presenter: E. Michael Golda (Homepage)

Event Dates:
  Friday April 18, 2014 from 11:00am to 12:00pm

A large naval warship ship is the most complex structure built by man.  The technology trends over the last 70 years have made automation a necessity for controlling the components, systems, and integrated systems of systems that make up a warship.  The presentation will provide a brief introduction of the ship as a system of systems.  The evolution of the Navy’s automation to intelligent agent-based distributed controls will be described.  In addition, opportunities for educational support and joint research with the Navy opportunities will be discussed.


Presenter's Biography:

E. Michael Golda, Ph.D., Chief Technologist in the Machinery Research and Engineering Department at the Naval Surface Warfare Center Carderock Division, Ship Systems Engineering Station, Philadelphia.

As the Chief Technologist of the Machinery Research and Engineering Department, Dr. Golda is responsible for the planning and execution of the research, development, and transition of new components and integrated machinery systems for future surface vessels and undersea vehicles.  Dr. Golda joined the Naval Surface Warfare Center, Carderock Division in 1992.  He has served in positions of increasing leadership responsibility in machinery research before being selected for his current position.  In 2009, Dr. Golda was awarded the Carderock Division Captain Harold E. Saunders Award For Exemplary Technical Management.

Dr. Golda graduated from the United States Naval Academy with a Bachelor of Science in Ocean Engineering.  He received a Masters and PhD in Materials Science and Engineering from Stevens Institute of Technology, Hoboken, New Jersey.  He is the author of twenty-four reports and papers.

Presenter: Martial Hebert (Homepage)

Event Dates:
  Friday March 21, 2014 from 11:00am to 12:00pm

Despite considerable progress in all aspects of machine perception, using machine vision in autonomous systems remains a formidable challenge. This is especially true in applications such as robotics, in which even a small error rate in the perception system can have catastrophic consequences for the overall system.

Presenter's Biography:

Martial Hebert is a Professor, Robotics Institute at Carnegie-Mellon University. His interest includes computer vision, especially recognition in images and video data, model building and object recognition from 3D data, and perception for mobile robots and for intelligent vehicles. His group has developed
approaches for object recognition and scene analysis in images, 3D point clouds, and video sequences.
In the area of machine perception for robotics, his group has developed techniques for people detection, tracking, and prediction, and for understanding the environment of ground vehicles from sensor data. He has served on the editorial boards the IEEE Transactions on Robotics and Automation, the IEEE transactions on Pattern Analysis and Machine Intelligence, and the International Journal of Computer Vision (for which he currently serves as Editor-in-Chief). He was Program Chair of the 2009 International Conference on Computer Vision, General Chair of the 2005 IEEE Conference on Computer Vision and Pattern Recognition and Program Chair  the 2013 edition of this conference.