Abandoned object detection: Datasets & Models
Detects unattended bags, packages, and other items left in public or restricted spaces using object detection on video or image feeds.
Abandoned object detection
This detection workflow scans video streams or still images from surveillance cameras and flags stationary items that have been left unattended in a monitored area. Trained on an abandoned object dataset, it locates and draws bounding boxes around suspicious items such as luggage, backpacks, packages, and boxes in public or restricted spaces.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate abandoned object detection
In security and surveillance settings, manually watching dozens of camera feeds for unattended items is tedious, error-prone, and impossible to scale across large facilities. Human operators miss objects during shift fatigue or when monitoring multiple screens, and by the time a threat is noticed it may be too late to respond. Automating abandoned object detection lets a vision model continuously scan every feed and flag stationary items the moment they appear, giving staff time to investigate. This shifts the workload from constant watching to responding only when something warrants attention.
Key benefits
A trained detection model provides consistent, round-the-clock monitoring across all camera feeds without adding headcount, and it integrates with existing CCTV and IP camera infrastructure. Alerts can be routed to security dashboards or access control systems, reducing response time to potential threats. The approach scales from a single entrance to entire airports, train stations, and stadiums using the same underlying model.
How to use it
- Upload an image: Drop any photo into the widget above to try abandoned object detection for free, right on this page.
- Preview instant results: The model detects backpack, suitcase, duffel bag, cardboard box, handbag 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 abandoned object 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 abandoned object detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Abandoned Object Detection project to Roboflow Agent.