English

Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup

Computer Vision and Pattern Recognition 2021-12-02 v1 Image and Video Processing

Abstract

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.

Keywords

Cite

@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}
}

Comments

8 pages, 10 figures

R2 v1 2026-06-23T17:20:28.011Z