MasterHow/CSFlow

[IV2022] pytorch implementation for 'CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving'

29
/ 100
Experimental

This project helps autonomous driving engineers analyze vehicle movement by precisely tracking how objects move across a sequence of camera images. It takes in pairs of consecutive video frames from a vehicle's cameras and outputs 'optical flow' data, which details the pixel-level motion between those frames. Autonomous driving perception engineers or researchers would use this to improve the vehicle's understanding of its surroundings.

No commits in the last 6 months.

Use this if you need highly accurate optical flow estimations from video streams to enhance autonomous vehicle navigation and perception systems.

Not ideal if your application is outside of autonomous driving, or if you need to run optical flow in real-time on resource-constrained embedded systems without dedicated AI acceleration.

autonomous-driving computer-vision motion-estimation vehicle-perception robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

37

Forks

2

Language

Python

License

MIT

Last pushed

Jun 30, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MasterHow/CSFlow"

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