Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs
(2023) 6th International ACM Workshop on Multimedia Content Analysis in Sports — Location: Ottawa, Canada (29.October.2023)
Files
Ball_Height___MMSPorts_20233.pdf
Open Access - Adobe PDF
- 3.18 MB
Details
- Authors
Van Zandycke, Gabriel 
- 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 im- age. 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 in- formation 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 https://github.com/gabriel-vanzandycke/deepsport.
- Affiliations
Citations
Caio, M. D., Van Zandycke, G., & De Vleeschouwer, C. (2023). Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs. 6th International ACM Workshop on Multimedia Content Analysis in Sports. Published. 6th International ACM Workshop on Multimedia Content Analysis in Sports, Ottawa, Canada. https://doi.org/10.1145/3606038.3616173