sekilab/VehicleOrientationDataset

The vehicle orientation dataset is a large-scale dataset containing more than one million annotations for vehicle detection with simultaneous orientation classification using a standard object detection network.

37
/ 100
Emerging

This dataset helps traffic analysts and city planners understand vehicle movement by providing image data annotated with vehicle types and their precise orientation (front, back, or side). It offers over a million annotations across various vehicle classes, directly usable for training models to detect and classify vehicles and their direction simultaneously. You would use this if you need to analyze traffic flow, optimize city planning, or improve smart city infrastructure based on detailed vehicle behavior.

No commits in the last 6 months.

Use this if you need to train or evaluate machine learning models for detecting vehicles and their orientation from image data for applications like traffic management or urban planning.

Not ideal if you only need basic vehicle detection without orientation, or if you require video-based analysis beyond static images.

traffic-analysis urban-planning smart-cities transportation-monitoring computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

86

Forks

9

Language

License

MIT

Last pushed

Sep 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/sekilab/VehicleOrientationDataset"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.