Detecting basketball elements with computer vision
A September 24, 2025 publication describes fine-tuning a detection model to identify players, jersey numbers, referees, the ball, and the hoop in basketball footage.
Source: RF-DETR fine-tunado para detecção no basquete (universe.roboflow.com). Text prepared with AI from this source.
What happened and what to do
On September 24, 2025, a publication described using a fine-tuned RF-DETR model to detect players, jersey numbers, referees, the ball, and the hoop in basketball scenes. The text also includes a link to a dataset for basketball player detection.
A company could apply this approach to structure game analysis: collect images or video, detect relevant elements, and store the results for review and tracking. A project could assess the dataset, adapt the model to the intended use, and integrate it through an API or dashboard, while respecting privacy rules and image rights.
How the consultancy can help
Wendelmaques can diagnose the opportunity and data requirements, scope model adaptation and integration, and implement the solution on the client's infrastructure, including operation and monitoring.
Next step
Send a short description of your video-analysis case to receive a scoped proposal.
Let's assess your project
I reply with scope and a proposal.