abel-gr/PedestrianCrossingIntention

Prediction of the intention of pedestrians to cross the street or not, using Graph Neural Networks and the coordinates of their skeleton that was previously generated using Openpose in the JAAD dataset.

12
/ 100
Experimental

This project helps self-driving car developers and urban planners predict whether a pedestrian intends to cross the street. It takes video footage of pedestrians, analyzes their skeleton movements over several frames, and outputs a prediction of whether they will cross or not in the near future. This helps improve pedestrian safety features in autonomous systems.

No commits in the last 6 months.

Use this if you need to anticipate pedestrian crossing behavior to enhance the safety and decision-making of autonomous vehicles or smart city infrastructure.

Not ideal if you require predictions for complex pedestrian behaviors beyond simple crossing intention or if your application involves environments significantly different from road scenarios.

autonomous-driving pedestrian-safety traffic-management urban-planning predictive-analytics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

Last pushed

Jul 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/abel-gr/PedestrianCrossingIntention"

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