Build with RF-DETR
Build a Player Tracking App Free with RF-DETR
Detect and follow every player, referee, and the ball across a match with a stable ID for each. Label footage, train RF-DETR free, and deploy it as a workflow.
- No credit card
- No ML team required
- Edge, on-prem or API
Build a Player Tracking App with Roboflow’s Free RF-DETR
In short
A player tracking app uses computer vision to detect each player, referee, and the ball in match video and follow them from frame to frame with a consistent ID. The model to train for it is RF-DETR, Roboflow's open-source real-time detection model, paired with a tracker such as ByteTrack. With Roboflow you label your footage, train RF-DETR for free, and deploy it as a workflow that returns annotated frames and tracked detections for every player.
How it works
The workflow behind the player tracking app
Use this Player Tracking with RF-DETR workflow: each frame goes to an RF-DETR model that finds players, goalkeepers, referees, and the ball, then through a confidence filter to a ByteTrack tracker that keeps each player's ID across frames. The tracked detections are drawn as boxes with their IDs. Every block is editable in the low-code builder, and the Roboflow Agent can build it from a description.
- output_image
- tracked_players
How to build a player tracking app with RF-DETR
Open the workflow and add your footage
Click "Use this free template" to copy the workflow into your Roboflow workspace. Upload frames from your own match footage, from the camera angle you will use, so the model sees your kits, pitch, and lighting.
Label players and train RF-DETR
Use Auto Label to draw boxes for player, goalkeeper, referee, and ball, then review and correct them. Train an RF-DETR model and select it in the detect_players block, or start with the pretrained soccer model already in the workflow.
Tune detection and tracking
Adjust the per-class thresholds in filter_by_confidence. The ball has a lower one because it is small and blurs in motion. In track_players, raise the lost track buffer if players often stay hidden behind each other for longer.
Deploy and run it on your video
Deploy the workflow as a Serverless Cloud API, or on your own hardware through Inference, to process live streams or recorded matches. Each frame returns output_image and tracked_players, with a tracking ID for every player to feed your stats or broadcast graphics.
Roboflow MCP
Build it from your AI assistant with the Roboflow MCP
Connect the Roboflow MCP Server to Claude, Cursor, or any MCP-compatible assistant and build the whole player tracking app in natural language, without leaving your editor.
Ask an assistant like Claude to search Roboflow Universe for soccer datasets, upload and auto-label your match frames, and train an RF-DETR model on player, goalkeeper, referee, and ball classes. It can then create and run the player tracking workflow on test frames and deploy it to your devices.
Paste it into your coding agent and it walks you through the rest. Setting up by hand? The server is https://mcp.roboflow.com/mcp.
Open the Roboflow listing, select Connect, then sign in to Roboflow. Available on desktop, web and mobile.
Run these commands in your terminal, then sign in to Roboflow. Claude Code CLI has no documented browser install link.
Opens the Roboflow plugin listing. Sign in if prompted and confirm the install on Cursor to add MCP and skills.
Opens the Roboflow plugin listing. Install the plugin and sign in to Roboflow when prompted to connect your account.
Opens the Roboflow plugin listing shared by ChatGPT and Codex. Install the plugin and sign in to Roboflow when prompted to connect your account.
Then run /mcp auth roboflow in Gemini CLI to sign in. Gemini CLI has no documented browser install link.
What your player tracking app can do
Trained on your footage, an RF-DETR model handles the specific, hard-to-catch cases that matter in a match:
- Keep each player's ID through tackles, crowds, and brief occlusions
- Tell players, goalkeepers, and referees apart
- Find the ball even when it is small and blurred by motion
- Follow players who sprint, turn, and change direction quickly
- Detect players far from the camera in wide broadcast shots
- Adapt to your league's kits, pitch, and camera angles
Want to customize your player tracking app?
Describe the player tracking app you want in plain English: the sport, the camera view, and what you want to track. The Roboflow Agent finds the data, trains an RF-DETR model, and assembles the workflow for you.
Open source
Roboflow’s RF-DETR is open source, Apache-2.0, and free to use
RF-DETR is an open-source, Apache-2.0 licensed real-time object detection model developed by Roboflow. The rfdetr Python package and most RF-DETR models are free to use, including in commercial products, and you can train and run everything on your own hardware. No account or lock-in required.
Apache-2.0 and free
The rfdetr package, Nano to Large detection, every segmentation size and Keypoint are Apache-2.0 licensed and free to use, including commercially.
Install and train locally
pip install rfdetr on Python 3.10+. Fine-tune on your own data in a few lines and run it entirely on your machine.
State of the art on COCO
RF-DETR is a real-time detector that is SOTA on COCO. RF-DETR-Large reaches 56.5 AP at 6.8 ms on an NVIDIA T4, and uses a DINOv2 backbone.
Deploy anywhere
Export to ONNX or TensorRT and run on GPU, CPU, or NVIDIA Jetson at the edge, or serve it through the Roboflow hosted API.
| Models | Licence |
|---|---|
| Detection: Nano, Small, Medium, Large | Apache-2.0 |
| Segmentation: every size, Nano to 2XLarge | Apache-2.0 |
| Keypoint (preview) | Apache-2.0 |
| Detection: Atto, Femto, Pico, XL, 2XL (rfdetr[plus]) | PML 1.0: commercial use included on Roboflow; commercial self-hosting needs the Enterprise add-on |
RF-DETR vs. other free detectors
A player tracking app has to detect every player on every frame, fast enough to keep up with live play. Here is how RF-DETR, fine-tuned on your own match footage, compares for real-time sports tracking.
| Model | Tasks | Best for | License |
|---|---|---|---|
| RF-DETR | Detection, segmentation (keypoints in preview) | Real-time detection you fine-tune on your own data, one model across tasks | Apache-2.0 (Nano to Large, all segmentation); PML 1.0 (Atto, Femto, Pico, XL, 2XL) |
| D-FINE | Detection | Precision localization when you do not need to fine-tune | Apache-2.0 |
| YOLO | Detection, segmentation, pose | Fast CNN-based detection with a large ecosystem | AGPL-3.0 (commercial license required for closed-source use) |
| GroundingDINO | Open-vocabulary detection | Finding objects by text prompt with no training, not real-time | Apache-2.0 |
| SAM 2 / SAM 3 | Segmentation | Pixel-precise masks; SAM 3 adds text-prompted segmentation | Apache-2.0 (SAM 2), SAM License (SAM 3) |
| Florence-2 | Vision-language | Reading, captioning, and OCR on images | MIT |
The takeaway for this app: RF-DETR runs in real time, so it keeps pace with live match video and gives the tracker clean detections on every frame. It fine-tunes well on small custom datasets and is open source, so you can adapt it to your sport and run it wherever your video is.
Build your player tracking app free today
Label, train, and deploy your player tracking app in one place.