Pedestrian detection: Datasets & Models
Detect and locate pedestrians in street-level and intersection camera feeds. Useful for traffic management, crossing safety, and smart city analytics.
Pedestrian detection
This detection workflow locates pedestrians in street-level and intersection imagery, drawing bounding boxes around each person walking, standing, or crossing in the scene. It accepts inputs from fixed traffic cameras, crosswalk sensors, and vehicle-mounted feeds, and can be trained or evaluated using a pedestrian dataset for traffic management and crossing safety applications.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate pedestrian detection
Manually monitoring intersections and sidewalks for pedestrian activity does not scale across a city's camera network, and human operators cannot watch hundreds of feeds around the clock. Automating pedestrian detection lets smart city and traffic teams continuously measure crossing volumes, detect people in unsafe zones, and feed real-time inputs to signal control systems. This replaces slow, error-prone review with consistent, timestamped detections you can act on immediately. The result is faster response to hazards and data-driven decisions about crosswalk placement and signal timing.
Key benefits
Automated detection runs on your existing traffic and intersection cameras, so there is no need to install new hardware to start collecting pedestrian counts and safety alerts. Detection accuracy holds up across day and night conditions and dense scenes, and the workflow scales from a single crossing to an entire municipal camera network. We recommend RF-DETR for its strong accuracy on small and partially occluded people typical of street scenes.
How to use it
- Upload an image: Drop any photo into the widget above to try pedestrian detection for free, right on this page.
- Preview instant results: The model detects pedestrian, cyclist, stroller, wheelchair, crosswalk 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 pedestrian 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 pedestrian detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Pedestrian Detection project to Roboflow Agent.