• Dataset 2009-12-01 (final round)
• Dataset 2009-11-30 (practice round)
• Dataset 2008-06-26 (final round)
• Dataset 2008-06-25 (practice round)
• Dataset 2007-07-25 (final round)
• Dataset 2007-07-24 (practice round)

• Pereira, R., and L. Seabra Lopes (2009) Learning Visual Object Categories with Global Descriptors and Local Features, Progress in Artificial Intelligence: 14th Portuguese Conference on Artificial Intelligence, EPIA 2009: Aveiro, Portugal, October 2009, Proceedings, LNCS 5816, Springer, 225-236.

• Pereira, R., L. Seabra Lopes, and A. Silva (2009) Semantic Image Search and Subset Selection for Classifier Training in Object Recognition, Progress in Artificial Intelligence: 14th Portuguese Conference on Artificial Intelligence, EPIA 2009: Aveiro, Portugal, October 2009, Proceedings, LNCS 5816, Springer, 338-349.

• Vijayanarasimhan, S., Grauman, K. Keywords to visual categories: Multiple-instance learning forweakly supervised object categorization, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-8, Anchorage, AK, June 2008. (local copy)

• D. Meger, P.-E. Forssén, K. Lai, S. Helmer, S. McCann, T. Southey, M. Baumann, J. J. Little, D. G. Lowe. Curious George: An Attentive Semantic Robot. Robotics and Autonomous Systems Journal, Special Issue From Sensors to Human Spatial Concepts, June 2008.

• Per-Erik Forssén, David Meger, Kevin Lai, Scott Helmer, James J. Little, David G. Lowe. Informed Visual Search: Combining Attention and Object Recognition. ICRA, May 2008.

• Scott Helmer, David Meger, Per-Erik Forssén, Tristram Southey, Sancho McCann, Pooyan Fazli, James J. Little, David G. Lowe. The UBC Semantic Robot Vision System. AAAI Technical Report, July 2007.

• David Meger, Per-Erik Forssén, Kevin Lai, Scott Helmer, Sancho McCann, Tristram Southey, Matthew Baumann, James J. Little, David G. Lowe, Bruce Dow. Curious George: An Attentive Semantic Robot. IROS07 Workshop - From Sensors to Human Spatial Concepts. November 2007.

• New Scientist : Robots Surf the Web to Learn about the World, 17 August 2007

• Artificial Intelligence and Robotics blog: Semantic Robot Vision Challenge video and results, July 26, 2007

Vision Research Resources

• Object categorization, Foundations and trends in Graphics and Vision.
  
  
• ICCV tutorial on ObjRec
  
  
• Learning Object Categories from Google's Image Search Fergus, R. , Fei-Fei L. , Perona, P. and Zisserman, A. Proc. of the 10th Inter. Conf. on Computer Vision, ICCV 2005.
  
  
• A Visual Category Filter for Google Images Fergus, R. , Perona, P. and Zisserman, A. Proc. of the 8th European Conf. on Computer Vision, ECCV 2004.
  
  
• Names and Faces, Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee Whye Teh, Erik Learned-Miller, David A. Forsyth. Under Submission.
  
  
• Animals on the Web Tamara L. Berg, David A. Forsyth Computer Vision and Pattern Recognition (CVPR) 2006

Hardware Resources

• 80/20 X-bar aluminum construction materials for building low-cost robots (this is what the ER1 is built from)

• Acroname robotics Distributers of robotic bases and controllers

  
  

• The ER1 Mobile Robot Kit Unfortunately discontinued... but you might be able to find some on ebay or through some other stores.

• Roomba Dev Tools Hardware to interface to a Roomba.

Vision Software Resources

• OpenCV C++ libraries for computer vision

• Digital Camera Support for UNIX, Linux and BSD

• GPhoto2 Digital Camera Software

• Linux IEEE1394 support

Robot Software Resources

• ERDOS: The Educational Robotics Drive-Operating-System A low-cost robotic control mechanism written by Zach Dodds at Harvey Mudd University.
  
  
• Python Robotics Python robotic control software for a very large number of different platforms.
  
  
• ROS The Robot Operating System from Willow Garage that subsumes Player/Stage and provides drivers from many modern sensor systems and robot platforms.
• Player/Stage C-based robot control and simulation software.

Web Crawling Resources

• Google Images Agent A Perl module that lets you automatically send a query to images.google.com and automatically download the first N hits.
  
  
• Exerpt from the Google Hacks O'Reilly book A chapter which gives some more details and a better example of how to write a Perl script using the above module to grab images from images.google.com.

1. For the robot league, are there any restrictions on the kind of robot hardware or sensors that can be used?
   
   
   • All computation must be carried on-board the robot.
     
     
   • There is no restriction on what the sensors are used. Note, however, that a single camera (which could be a single camera from a stereo pair for instance) must be used to generate the images to be submitted for scoring.
     
     
   • Robots must be able to be used safely indoors without damaging or marking carpets. Thus if a skid steer vehicle is to be used, it must have tires that will easily slide on the carpet.
     
     
   
   
2. What is the difference between qualification and registration?
   
   
   • Here are some relevant terms:
     
     
     1. Pre-registration : this merely states that the team is intending to participate in the SRVC or another event. SRVC teams still must qualify before they can register and all teams must register before they can attend and participate in the event.

         

     2. Qualification : teams must pass an initial test and/or provide details about their approach and team to the organizers. This is required before the teams will be allowed to participate in the event. For more details, please see the Qualification section.
        
        

     3. Registration : teams that have qualified are allowed to register for the event and participate when it is run. For more details, please see the Registration section.