Spiideo SoccerNet SynLoc : Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data
(2025) 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2025 p.278-285- Abstract
Currently, most research and public datasets for video sports analytics are base on detecting players as bounding boxes in broadcast videos. Going from there to precise locations on the pitch is however hard. Modern solutions are making dedicated static cameras covering the entire pitch more readily accessible, and they are now used more and more even in lower tiers. To promote research that can take benefits of such cameras and produce more precise pitch locations, we introduce the Spiideo SoccerNet SynLoc dataset. It consists of synthetic athletes rendered on top of images from real world installation of such cameras. We also introduce a new task of detecting the players in the world pitch coordinate system and a new metric based... (More)
Currently, most research and public datasets for video sports analytics are base on detecting players as bounding boxes in broadcast videos. Going from there to precise locations on the pitch is however hard. Modern solutions are making dedicated static cameras covering the entire pitch more readily accessible, and they are now used more and more even in lower tiers. To promote research that can take benefits of such cameras and produce more precise pitch locations, we introduce the Spiideo SoccerNet SynLoc dataset. It consists of synthetic athletes rendered on top of images from real world installation of such cameras. We also introduce a new task of detecting the players in the world pitch coordinate system and a new metric based solely on real world physical properties where the representation in the image is irrelevant. The dataset and code are publicly available at https://github.com/Spiideo/sskit.
(Less)
- author
- Ardö, Håkan
LU
; Nilsson, Mikael
LU
; Cioppa, Anthony ; Magera, Floriane ; Giancola, Silvio ; Liu, Haochen ; Ghanem, Bernard and Van Droogenbroeck, Marc
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- 3D, Dataset, Detection, Human, Localization, Sports, Synthetic
- host publication
- Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
- pages
- 8 pages
- conference name
- 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2025
- conference location
- Porto, Portugal
- conference dates
- 2025-02-26 - 2025-02-28
- external identifiers
-
- scopus:105001840108
- DOI
- 10.5220/0013108200003912
- language
- English
- LU publication?
- yes
- id
- d763ec66-e94a-46dc-9126-cef74ce67862
- date added to LUP
- 2025-09-01 13:28:21
- date last changed
- 2025-09-01 13:29:04
@inproceedings{d763ec66-e94a-46dc-9126-cef74ce67862, abstract = {{<p>Currently, most research and public datasets for video sports analytics are base on detecting players as bounding boxes in broadcast videos. Going from there to precise locations on the pitch is however hard. Modern solutions are making dedicated static cameras covering the entire pitch more readily accessible, and they are now used more and more even in lower tiers. To promote research that can take benefits of such cameras and produce more precise pitch locations, we introduce the Spiideo SoccerNet SynLoc dataset. It consists of synthetic athletes rendered on top of images from real world installation of such cameras. We also introduce a new task of detecting the players in the world pitch coordinate system and a new metric based solely on real world physical properties where the representation in the image is irrelevant. The dataset and code are publicly available at https://github.com/Spiideo/sskit.</p>}}, author = {{Ardö, Håkan and Nilsson, Mikael and Cioppa, Anthony and Magera, Floriane and Giancola, Silvio and Liu, Haochen and Ghanem, Bernard and Van Droogenbroeck, Marc}}, booktitle = {{Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications}}, keywords = {{3D; Dataset; Detection; Human; Localization; Sports; Synthetic}}, language = {{eng}}, pages = {{278--285}}, title = {{Spiideo SoccerNet SynLoc : Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data}}, url = {{http://dx.doi.org/10.5220/0013108200003912}}, doi = {{10.5220/0013108200003912}}, year = {{2025}}, }