Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs

TL;DR

This paper introduces a novel method for 3D basketball localization from a single calibrated image, utilizing height prediction and projection matrix exploitation, significantly improving accuracy in sports analytics applications.

Contribution

The work presents a new approach for 3D object localization in sports, specifically basketballs, from a single image using height estimation and camera calibration data, with extensive experimental validation.

Findings

Substantial accuracy improvements over recent methods.

Effective 3D localization using only a single image and known calibration.

Open-source code available for reproducibility.

Abstract

Accurately localizing objects in three dimensions (3D) is crucial for various computer vision applications, such as robotics, autonomous driving, and augmented reality. This task finds another important application in sports analytics and, in this work, we present a novel method for 3D basketball localization from a single calibrated image. Our approach predicts the object's height in pixels in image space by estimating its projection onto the ground plane within the image, leveraging the image itself and the object's location as inputs. The 3D coordinates of the ball are then reconstructed by exploiting the known projection matrix. Extensive experiments on the public DeepSport dataset, which provides ground truth annotations for 3D ball location alongside camera calibration information for each image, demonstrate the effectiveness of our method, offering substantial accuracy improvements compared to recent work. Our work opens up new possibilities for enhanced ball tracking and understanding, advancing computer vision in diverse domains. The source code of this work is made publicly available at \url{https://github.com/gabriel-vanzandycke/deepsport}.