[robocup-small] SSL-Vision

[Stefan Zickler]

Hi All,

this is a status update on the Small Size League Shared Vision System
(SSL-Vision).

All basic functionality of the system has been implemented at this
point. In fact, we already had some very successful tests, allowing a
full robot team to run with SSL-Vision. While there are continuing
efforts to further improve the usability and performance of the
system, we believe that SSL-Vision is now in a state where teams
should feel confident enough to test it with their own cameras and
robots.

SSL-Vision's official project site is here: http://code.google.com/p/ssl-vision/

Documenting the entire system is an ongoing process, but most
questions should already be answered in the existing wiki pages:
http://code.google.com/p/ssl-vision/wiki/Manual

To obtain the latest version of the code, please use anonymous svn checkout:
http://code.google.com/p/ssl-vision/source/checkout

To compile the code, take a look at the requirements and installation page:
http://code.google.com/p/ssl-vision/wiki/RequirementsInstallation

Mini-FAQ:
What does SSL-Vision do?
SSL-Vision provides a complete multi-camera image processing system
for the RoboCup Small Size League Domain. It provides a coherent
interface to allow adjustment of calibration parameters of all
components, including capture, geometry, color thresholding, and
pattern detection. Its detection results include IDs, positions,
orientations, and confidences of all robots, as well as position and
confidence of the ball. SSL-Vision currently supports IEEE1394 / DCAM
cameras, but support for other capture methods can be easily added
into the framework if required.

What does SSL-Vision NOT do?
SSL-Vision does not perform any sensor-merging, thus it will deliver
detection results from both cameras independently. It is up to the
teams to merge robots or balls which happen to overlap between the two
cameras' observations. Similarly, SSL-Vision does not perform any
tracking or smoothing of objects. This is left to the teams as it will
allow them to integrate their own predicted executions into their
respective tracking components.

Your feedback is appreciated. Bugs can be reported using the issue tracker:
http://code.google.com/p/ssl-vision/issues/list

Other issues, questions, and feature requests should be posted to the
development mailing list:
http://groups.google.com/group/ssl-vision

We strongly encourage teams to try using SSL-Vision during local competitions!

Best Regards,
Stefan (On behalf of all the SSL-Vision developers)