Graffiti detection: Datasets & Models
Automatically detect and locate graffiti on walls, bridges, signage, and other public infrastructure from camera imagery. Flags vandalism for review so cities can prioritize cleanup.
Graffiti detection
This graffiti detection workflow uses object detection to locate graffiti and unauthorized markings in images from municipal cameras, vehicle-mounted cameras, or field-collected photos. It returns bounding boxes around affected surfaces such as walls, bridges, utility boxes, road signs, and transit infrastructure so cities can flag vandalism and prioritize cleanup.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate graffiti detection
Manually inspecting streets, underpasses, and transit stops for graffiti is slow, inconsistent, and expensive, and vandalism often goes unreported until it accumulates. Automating graffiti detection lets municipalities scan imagery at scale, surface new markings quickly, and route cleanup crews before the problem spreads. This shortens the time between when graffiti appears and when it is remediated, which is a known factor in deterring repeat vandalism. It also produces a consistent, auditable record of where and when incidents occur.
Key benefits
Faster detection means faster cleanup, fewer manual inspections, and better allocation of maintenance crews across a city. The workflow integrates with existing municipal camera feeds, dashcams, and mobile phone captures, so teams can deploy without new hardware. Detection scales from a single problem corridor to an entire transit network as coverage grows.
How to use it
- Upload an image: Drop any photo into the widget above to try graffiti detection for free, right on this page.
- Preview instant results: The model detects graffiti, tagged wall, spray paint can, road sign, utility box within seconds and returns an annotated image with structured predictions, so you can immediately see how well it works. Adjust the detection classes and re-run until the results fit your scenario.
- Like what you see?: With a free Roboflow account, you can deploy this workflow with the Serverless Cloud API, customize it in your workspace, or train RF-DETR on your own images for production accuracy.
- Get started for free: No code or training data required to begin: upload, review the results, and make it part of your stack in a single click.
Recommended model for graffiti detection
RF-DETR is state of the art for real-time object detection, instance segmentation, and keypoint detection, with higher accuracy and lower latency than comparable models, and it's Apache 2.0 licensed. When you're ready to build a production model for graffiti detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Graffiti Detection project to Roboflow Agent.