This paper considers the task of detecting the ball from a single viewpoint in the challenging but common case where the ball interacts frequently with players while being poorly contrasted with respect to the background. We propose a novel approach by formulating the problem as a segmentation task solved by an efficient CNN architecture. To take advantage of the ball dynamics, the network is fed with a pair of consecutive images. Our inference model can run in real time without the delay induced by a temporal analysis. We also show that test-time data augmentation allows for a significant increase the detection accuracy. As an additional contribution, we publicly release the dataset on which this work is based.
@article{arxiv.2007.11876,
title = {Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup},
author = {Gabriel Van Zandycke and Christophe De Vleeschouwer},
journal= {arXiv preprint arXiv:2007.11876},
year = {2021}
}