Build with RF-DETR
Build a Crack Detection App Free with RF-DETR
Find and box cracks in concrete walls, slabs, and structures and get a pass or fail result with a crack count. Label images, train RF-DETR free, and deploy it as a workflow.
- No credit card
- No ML team required
- Edge, on-prem or API
Build a Crack Detection App with Roboflow’s Free RF-DETR
In short
A crack detection app uses computer vision to inspect photos of concrete and other surfaces, draws a box around each crack it finds, and flags any surface that needs repair. The model to train for it is RF-DETR, Roboflow's open-source real-time detection model. With Roboflow you label your images, train RF-DETR for free, and deploy it as a workflow that returns an annotated image, a crack count, and a PASS or FAIL result.
How it works
The workflow behind the crack detection app
Use this Crack Detection with RF-DETR workflow: each image goes to an RF-DETR model that finds cracks in the surface, then through a confidence filter and into two tracks. One counts the cracks and turns the count into PASS or FAIL, the other draws boxes and labels, and both meet where the verdict is 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
- inspection_result
- crack_count
- predictions
How to build a crack detection app with RF-DETR
Open the workflow and add your images
Click "Use this free template" to copy the workflow into your Roboflow workspace. Upload photos of the surfaces you inspect, taken the way you will capture them in the field, including clean surfaces and examples of hairline, wide, and branching cracks.
Label cracks and train RF-DETR
Use Auto Label to box each crack, then review and correct the results, paying close attention to thin hairline cracks. Train an RF-DETR model and select it in the detect_cracks block. RF-DETR fine-tunes well on small custom datasets, so you can start with the examples you have.
Tune the threshold and the pass/fail rule
Set the threshold in filter_by_confidence so real cracks are caught without flagging joints, stains, or surface texture. Raise the count in pass_fail_result if a few minor cracks are acceptable on your surfaces.
Deploy and connect it to your inspections
Deploy the workflow as a Serverless Cloud API, or on your own hardware through Inference, including cameras and drones in the field. Each run returns output_image, inspection_result, crack_count, and predictions for your inspection reports or maintenance system.
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 crack detection app in natural language, without leaving your editor.
Ask an assistant like Codex or ChatGPT to search Roboflow Universe for concrete crack datasets, upload and auto-label your inspection photos, and train an RF-DETR model to find cracks. It can then create and run the crack detection 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 crack detection app can do
Trained on your images, an RF-DETR model handles the specific, hard-to-catch cases that matter in your inspections:
- Spot thin hairline cracks before they widen
- Find cracks in walls, slabs, columns, and bridge decks
- Tell cracks apart from joints, stains, and surface texture
- Count every crack in an image for your inspection report
- Inspect photos from phones, fixed cameras, and drones
- Flag surfaces that need repair without a manual review of every photo
Want to customize your crack detection app?
Describe the crack detection app you want in plain English: the surfaces you inspect, the cracks you need to catch, and what should happen when one is found. 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 crack detection app has to find thin, irregular cracks across large surfaces, often in uneven light and among joints and stains, so the model needs to be both accurate and fast. Here is how RF-DETR, fine-tuned on your own inspection images, compares for real-time 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 inspect every photo or video frame as it comes in. It fine-tunes well on small custom datasets and is open source, so you can train on your own surfaces and run the model wherever you need it.
Build your crack detection app free today
Label, train, and deploy your crack detection app in one place.