tobybreckon/fire-detection-cnn

real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)

51
/ 100
Established

This project helps operations engineers and safety managers automatically detect fires in real-time from video feeds or still images. It takes raw video or image data as input and outputs whether a fire is present, and optionally, precisely where it's located within the frame. This is useful for monitoring sensitive areas without constant human supervision.

570 stars. No commits in the last 6 months.

Use this if you need a reliable, real-time system for automated fire detection in surveillance footage or live camera feeds.

Not ideal if you require an extremely low false positive rate at very high frame rates, or need a system that learns specific fire patterns from your unique environment without pre-trained models.

fire-safety industrial-monitoring surveillance hazard-detection operations-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

570

Forks

173

Language

Python

License

MIT

Last pushed

Jul 22, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tobybreckon/fire-detection-cnn"

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