Build with RF-DETR
Build a Shelf Monitoring App Free with RF-DETR
Spot empty and low-stock facings on every shelf and know what needs restocking. Label shelf photos, train RF-DETR free, and deploy it as a workflow.
- No credit card
- No ML team required
- Edge, on-prem or API
Build a Shelf Monitoring App with Roboflow’s Free RF-DETR
In short
A shelf monitoring app uses computer vision to scan store shelves and find out-of-stock gaps and facings that are running low, so staff know exactly what to restock. The model to train for it is RF-DETR, Roboflow's open-source real-time detection model. With Roboflow you label your shelf photos, train RF-DETR for free, and deploy it as a workflow that returns an annotated image, counts of empty and low-stock spots, and a RESTOCK or OK status.
How it works
The workflow behind the shelf monitoring app
Use this Shelf Monitoring with RF-DETR workflow: each shelf photo goes to an RF-DETR model that finds empty spaces and low-stock facings, then through a per-class confidence filter. Two counters tally the empty and low-stock spots and the empty count sets the RESTOCK or OK status, while the other track draws boxes and labels, and both meet where the status and counts are written onto the image. Every block is editable in the low-code builder, and the Roboflow Agent can build it from a description.
- output_image
- restock_status
- empty_count
- low_stock_count
- predictions
How to build a shelf monitoring app with RF-DETR
Open the workflow and add your shelf photos
Click "Use this free template" to copy the workflow into your Roboflow workspace. Upload shelf photos from the phones, cameras, or robots you use, including full, partly stocked, and empty shelves.
Label gaps and train RF-DETR
Use Auto Label to box each empty space and low-stock facing, then review and correct the results. Train an RF-DETR model and select it in the detect_shelf_gaps block. RF-DETR fine-tunes well on small custom datasets, so you can start with the photos you have.
Tune the thresholds and the restock rule
Set the thresholds in filter_by_confidence for empty and low-stock spots. Change the rule in restock_status if, for example, a shelf with several low-stock facings should also trigger a restock.
Deploy and connect it to your stores
Deploy the workflow as a Serverless Cloud API, or on your own hardware through Inference. Each image returns output_image, restock_status, empty_count, low_stock_count, and predictions for your replenishment system, task app, or dashboard to act on.
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 shelf monitoring app in natural language, without leaving your editor.
Ask an assistant like Codex or ChatGPT to search Roboflow Universe for out-of-stock datasets, upload and auto-label your shelf photos, and train an RF-DETR model on empty space and reduced stock classes. It can then create and run the shelf monitoring workflow on test images 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 shelf monitoring app can do
Trained on your shelf photos, an RF-DETR model handles the specific, hard-to-catch cases that matter in your store:
- Find empty spaces even when products behind them are pushed back
- Tell low-stock facings apart from fully stocked ones
- Spot gaps between tightly packed products on crowded shelves
- Keep detecting through glare from shelf lighting and glossy packaging
- Check every shelf in an aisle from one walk or camera pass
- Flag what needs restocking before customers find an empty shelf
Want to customize your shelf monitoring app?
Describe the shelf monitoring app you want in plain English: your store, your shelves, and what counts as needing a restock. 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 shelf monitoring app has to find small gaps between dozens of tightly packed products in every shelf photo, so the model needs to be both accurate and fast. Here is how RF-DETR, fine-tuned on your own shelf photos, compares for retail detection.
| 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 can process shelf photos and camera feeds across many stores. It fine-tunes well on small custom datasets and is open source, so you can train on your own shelves and run the model wherever your cameras are.
Build your shelf monitoring app free today
Label, train, and deploy your shelf monitoring app in one place.