Streetlight detection: Datasets & Models
Streetlight detection uses computer vision to locate and classify streetlights and their components in imagery from street-level cameras, drones, or vehicle-mounted sensors. It automates asset identification across urban and roadway environments.
Streetlight detection
This streetlight detection workflow uses object detection to locate streetlights and their components, including lamp heads, poles, and mounting arms, drawing a bounding box around each detected object. It accepts images and video frames from street-level cameras, dashcams, aerial drones, or fixed municipal cameras, making it suitable for automated asset inventory across urban and roadway environments.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate streetlight detection
Manually inventorying streetlights across a city means dispatching crews to drive or walk every road and log each fixture by hand, a slow and error-prone process that quickly goes stale as assets are added or removed. Automating streetlight detection lets a municipality process existing camera or drone footage to build and continuously update a lighting asset map without repeated field visits. This supports maintenance planning, outage tracking, energy audits, and infrastructure compliance. The result is faster surveys, more accurate counts, and a repeatable pipeline you control.
Key benefits
Teams can process large volumes of street-level and aerial imagery to produce consistent, geotagged streetlight inventories rather than relying on intermittent manual audits. The workflow integrates with cameras, drones, and vehicle-mounted rigs you likely already operate, and RF-DETR delivers accurate detection that scales from a single corridor to an entire city network. Detections can be exported to GIS and asset-management systems to keep infrastructure records current.
How to use it
- Upload an image: Drop any photo into the widget above to try streetlight detection for free, right on this page.
- Preview instant results: The model detects streetlight, light pole, lamp head, utility pole, traffic light 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 streetlight 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 streetlight detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Streetlight Detection project to Roboflow Agent.