[opensource] Employment Recruitment Opportunity for Students

T Cramer cramer.85 at osu.edu
Fri May 20 10:45:00 EDT 2005


We have a unique opportunity for students and researchers to meet with a 
GE Employment Recruiter.

Tuesday, May 24th, 5:00, DL 874 (Lounge)

Following his talk at 3:30 in DL 480, Dr. Jens Ritchser would like to 
meet with students and researchers who have an interest in pursuing 
careers at GE Global Research. Candidates with long term and/or short 
term employment interests in GE R&D Centers located in Bangalore, India 
and Niskayuna, NY are encouraged to attend the talk and meet with Dr. 
Rittscher.  Please provide any relevant material (CVs etc.) if you are 
interested in a career with GE.


The talk will concern:

Simultaneous Estimation of Segmentation and Shape

Jens Rittscher
Visualization and Computer Vision, GE Global Research, Niskayuna, NY

Room: DL 480
Talk: Tuesday May 24, 2005, 3:30-4:30.

The main focus of this work is the integration of feature grouping and 
model based segmentation into one consistent framework.  The algorithm 
is based on partitioning a given set of image features using a 
likelihood function that is parameterized on the shape and location of 
potential individuals in the scene.  Using a variant of the EM 
formulation, maximum likelihood estimates of both the model parameters 
and the grouping are obtained simultaneously.  The resulting algorithm 
performs global optimization and generates accurate results even when 
decisions can not be made using local context alone.  An important 
feature of the algorithm is that the number of people in the scene is 
not modeled explicitly.  As a result no prior knowledge or assumed 
distributions are required.  The approach is shown to be robust with 
respect to partial occlusion, shadows, clutter, and can operate over a 
large range of challenging view angles including those that are parallel 
to the ground plane.  Comparisons with existing crowd segmentation 
systems are made and the utility of coupling crowd segmentation with a 
temporal tracking system is demonstrated.

In addition to presenting the mathematical formulation of the algorithm 
the talk will illustrate on how the algorithm is used for practical 
applications (e.g. people counting).  The application of the algorithm 
is not limited to video surveillance and it will be shown how more 
elaborate shape models can be included into the formulation.

Bio:
Jens Ritchser is a Senior Researcher in Visualization and Computer 
Vision at GE Global Research, Niskayuna, NY.  He received his Diploma in 
Mathematics from the University of Bonn, and his Doctoral degree in 
Electrical Engineering from University of Oxford (under the supervision 
of Andrew Blake).  He later continued as a post-doctoral researcher at 
Oxford under the tutelage of A. Zisserman for a period of three months. 
  He joined GE Global Research in the year 2001.


More information about the Opensource mailing list