Can I read Ball 3D Localization From A Single Calibrated Image on EtoBox?

Ball 3D Localization From A Single Calibrated Image by Van Zandycke, Gabriel; De Vleeschouwer, Christophe is a scholarly article available to read on EtoBox.

What is Ball 3D Localization From A Single Calibrated Image about?

Ball 3D localization in team sports has various applications including automatic offside detection in soccer, or shot release localization in basketball. Today, this task is either resolved by using expensive multi-views setups, or by restricting the analysis to ballistic trajectories. In this work, we propose to address the task on a single image from a calibrated monocular camera by estimating ball diameter in pixels and use the knowledge of real ball diameter in meters. This approach is suitable for any game situation where the ball is (even partly) visible. To achieve this, we use a small neural network trained on image patches around candidates generated by a conventional ball detector. Besides predicting ball diameter, our network outputs the confidence of having a ball in the image patch. Validations on 3 basketball datasets reveals that our model gives remarkable predictions on ball 3D localization. In addition, through its confidence output, our model improves the detection rate by filtering the candidates produced by the detector. The contributions of this work are (i) the first model to address 3D ball localization on a single image, (ii) an effective method for ball 3D

Author

Van Zandycke, Gabriel; De Vleeschouwer, Christophe

Published

2022

Language

EN