[robotics-worldwide] CFP: 3rd Semantic Robot Vision Challenge 2009
roehrbei at informatik.uni-bremen.de
roehrbei at informatik.uni-bremen.de
Tue Apr 28 07:39:28 PDT 2009
Call for Participation for the
THIRD SEMANTIC ROBOT VISION CHALLENGE - A Special Track of the ISVC 2009
The Semantic Robot Vision Challenge (SRVC) is a research competition
that is designed to advance the state of the art in embodied vision,
active scene understanding, and automatic acquisition of knowledge
from the Internet. This competition is an indoor robotic photo
scavenger hunt. Teams will be required to demonstrate a robot that has
the ability to:
1. Read and parse a textual list of generic or specific objects to be
found in the environment. Examples from 2008 include frying pan,
upright vacuum cleaner and Ritz Crackers.
2. Autonomously connect to the Internet and build an object
classification database from images or other information related to
the listed objects, in a set amount of time.
3. Autonomously navigate and search the unknown environment with the
task of taking snapshots of the listed objects using the data acquired
from the Internet.
4. Return an image of each object type containing a single bounding
box around the pictured object.
Unlike with computer vision competitions, participants must address
many issues of embodied vision. Robots must recognize objects in
lighting conditions and configurations that can give them very unusual
appearance, but can use navigation to look at objects from angles that
are close to the canonical views used in Internet images. Also, as in
the real world, scene context can be used to guide the search for
objects to areas which make the most sense for them to be found (e.g.
a stapler is usually found on a desk rather than on the floor or on a
wall). In this competition, objects in the scene will be placed in a
way that should improve recognition results for robots that take
advantage of scene context understanding.
Teams can choose to participate in one of two different leagues:
A. Robot league: Teams bring their own robot to participate in the event.
B. Software league: Teams bring only a computer to run their software.
The visual data is collected immediately before the event by a robot
run by the organizers.
We encourage anyone in these research fields to participate and help
us to advance the state of the art in embodied vision and scene
understanding. At the end of the competition, we will hold a workshop
so that the specific technical aspects of each entry can be presented
and discussed. The competition will be held at the 5th International
Symposium on Visual Computing (ISVC), which takes place in Las Vegas,
Nevada, from November 30th to December 2nd. For details see:
Qualification Material Submission Deadline: September 14, 2009
Acceptance Notification: September 28, 2009
ISVC09 Symposium: November 30 - December 2, 2009
Competition Date: December 1, 2009
See http://www.semantic-robot-vision-challenge.org for more details on
participation and qualification. If interested, subscribe to our email
list! Please send an email to Paul Rybski and Daniel DeMenthon if you
would like to participate.
Paul E. Rybski (prybski at cs.cmu.edu), Carnegie Mellon University, USA
Daniel DeMenthon (Daniel.DeMenthon at jhuapl.edu), Johns Hopkins University, USA
Cornelia Fermuller (fer at umiacs.umd.edu), University of Maryland, USA
Pooyan Fazli (pooyanf at cs.ubc.ca), University of British Columbia, Canada
Ajay Mishra (mishraka at umiacs.umd.edu), University of Maryland, USA
Luis Seabra Lopes (lsl at ua.pt), Universidade de Aveiro, Portugal
Florian Roehrbein (roehrbei at informatik.uni-bremen.de), Universitaet
David Gustafson (dag at ksu.edu), Kansas State University, USA
Dr. Florian Röhrbein
FB 3 Informatik und Mathematik
Postfach 330 440
28334 Bremen, Germany
e-mail: roehrbei at informatik.uni-bremen.de
More information about the robotics-worldwide