NeilNie/speed_estimation

Using deep learning to predict the speed of a moving vehicle.

29
/ 100
Experimental

Leverages DeepMind's Inflated 3D ConvNet (i3D) architecture to extract spatial-temporal features from video sequences, enabling regression of vehicle speed beyond single-frame prediction. The model inflates 2D ImageNet-pretrained filters into 3D convolutions for seamless video understanding, with final layers adapted for continuous speed output. Includes visualization techniques demonstrating learned traffic behaviors like stopping and yielding patterns.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

11

Forks

4

Language

Python

License

MIT

Last pushed

Sep 15, 2018

Commits (30d)

0

Get this data via API

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

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