ltkong218/FastFlowNet

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation (ICRA 2021)

44
/ 100
Emerging

This project helps robotic vision engineers and embedded systems developers analyze motion in video by estimating optical flow. It takes in two adjacent video frames and outputs a visual representation of the motion vectors between them, indicating how pixels move from one frame to the next. This is particularly useful for those building real-time vision systems for drones, autonomous vehicles, or surveillance on resource-constrained devices.

320 stars. No commits in the last 6 months.

Use this if you need to perform fast, accurate motion analysis on video feeds using minimal computational resources, especially on embedded devices like NVIDIA Jetson.

Not ideal if your primary concern is absolute top-tier accuracy at the cost of speed and you have access to powerful desktop GPUs or cloud computing.

robotics embedded-vision motion-tracking computer-vision real-time-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

320

Forks

44

Language

Python

License

MIT

Last pushed

Aug 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ltkong218/FastFlowNet"

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