ika-rwth-aachen/Cam2BEV

TensorFlow Implementation for Computing a Semantically Segmented Bird's Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.

50
/ 100
Established

This project helps automotive engineers and researchers transform multiple camera views from a vehicle into a single, comprehensive bird's-eye view (BEV) image. It takes raw camera images and outputs a semantically segmented BEV image, highlighting elements like roads, vehicles, and pedestrians, even predicting occluded areas. This is crucial for developing and testing advanced driver assistance systems and autonomous driving functionalities.

780 stars. No commits in the last 6 months.

Use this if you need to understand a vehicle's surroundings from a top-down perspective using multiple camera feeds for automated driving research or development.

Not ideal if your application doesn't involve vehicle-mounted cameras, requires real-time processing on very constrained hardware, or you need highly precise distance measurements for non-flat surfaces without semantic segmentation.

autonomous-driving advanced-driver-assistance-systems automotive-perception environment-sensing vehicle-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

780

Forks

124

Language

Python

License

MIT

Last pushed

May 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ika-rwth-aachen/Cam2BEV"

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