Skip to content
Nicolai Ommer edited this page May 27, 2018 · 9 revisions

Introduction

In the past, RoboCup Small Size League rules allowed every team to set up their own global vision system as a primary sensor. This option beared several organizational limitations and costs for the teams, thus impairing the league's progress. Additionally, most teams had converged on similar solutions and produced few significant research results to this global vision problem over the last years.

In 2009, the league committees decided to migrate to a shared vision system (including hardware) that could be used by all teams. This system - named SSL-Vision - is currently developed by volunteers from participating teams. This manual describes the current state and usage of SSL-Vision.

A paper describing SSL-Vision is available here (Bibtex file available here).

Example Configuration

If you are new to ssl-vision and want to get used to it, you can start with a ready to use config with images from a real field. Note, that the field has the dimensions of the single sized field, but with four cameras (due to limited room height).

Standard Marker Colours

As of RoboCup 2015, teams were required to purchase their own colored paper for robot markers instead of receiving it at the competition. For RoboCup 2018, LOC will provide paper at the competition again. OC/TC/LOC will try to find good colors. Some of the standard colors from last years were not ideal.

The standard marker papers until RoboCup 2017 were:

Contents

Requirements and Installation
Capturing Images
Field Configuration and Camera Calibration
Color Segmentation Configuration
Team Configuration
Communication and Sample Clients
Open Issues
Development Processes