daniel-bogdoll/unknown_objects_roads

Repository of the paper Multimodal Detection of Unknown Objects on Roads for Autonomous Driving at IEEE SMC

32
/ 100
Emerging

This project helps automotive safety engineers or validation teams enhance the reliability of autonomous vehicles by identifying objects on the road that the vehicle's standard detection system might miss. It takes in camera images and LiDAR sensor data and outputs detections of 'unknown' objects within the driving area. This tool is designed for specialists involved in validating and improving autonomous driving systems.

No commits in the last 6 months.

Use this if you need to identify unexpected or novel objects on the road that your autonomous vehicle's existing object detection models are not trained to recognize, helping to uncover potential corner cases for improved safety.

Not ideal if you are looking for a general-purpose object detection system for commonly encountered objects like cars, pedestrians, or traffic signs.

autonomous-driving vehicle-safety sensor-fusion edge-case-detection AD-validation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

30

Forks

10

Language

Jupyter Notebook

License

Last pushed

May 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/daniel-bogdoll/unknown_objects_roads"

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