The rUNSWift SPL Field Segmentation Dataset

TL;DR

This paper introduces a new dataset of 20 high-resolution videos with labels for soccer field segmentation, aimed at improving robot vision in RoboCup SPL under various conditions.

Contribution

The paper provides a publicly available, annotated dataset specifically designed for training and evaluating field segmentation algorithms in RoboCup SPL.

Findings

Dataset includes diverse lighting and calibration conditions

High-resolution videos with accurate field labels

Facilitates development of robust segmentation methods

Abstract

In RoboCup SPL, soccer field segmentation has been widely recognised as one of the most critical robot vision problems. Key challenges include dynamic light condition, different calibration status for individual robot, various camera prospective and more. In this paper, we propose a dataset that contains 20 videos recorded with Nao V5/V6 humanroid robots by team rUNSWift under different circumstances. Each of the videos contains several consecutive high resolution frames and the corresponding labels for field. We propose this dataset to provide training data for the league to overcome field segmentation problem. The dataset will be available online for download. Details of annotation and example of usage will be explained in later sections.