Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

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)

47MITPython

View on GitHub

Stars: 571
Forks: 173
Watchers: 571
Open issues: 3
Contributors: 5

Star history, last 90 days+1 over 7 snapshots

2026-07-24 · 5702026-08-06 · 571

Star history, last 90 days
Date	Stars
2026-07-24	570
2026-07-25	570
2026-07-28	569
2026-07-30	569
2026-07-31	570
2026-08-04	571
2026-08-06	571

Today

— stars today

This week

+2 stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.35%/day

From the README

# Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection

[and subsequent follow on work: _Experimental Exploration of Compact Convolutional Neural Network Architectures
for Non-temporal Real-time Fire Detection_]

![Python Build/Test](https://github.com/tobybreckon/fire-detection-cnn/workflows/Python%20Build/Test/badge.svg) Tested using Python 3.7.x, [TensorFlow 1.15](https://www.tensorflow.org/install/), [TFLearn 0.3.2](http://tflearn.org/) and [OpenCV 3.x / 4.x](http://www.opencv.org) (requires opencv extra modules - ximgproc module for superpixel segmentation)

## Architectures:
![FireNet](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/FireNet.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;FireNet architecture (above)
![InceptionV1-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV1-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV1-OnFire architecture (above)
![InceptionV3-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV3-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV3-OnFire architecture (above)
![InceptionV4-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV4-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV4-OnFire architecture (above)


## New Updated Architecture and Pytorch Models for Fire Detection available -- ![HERE](https://github.com/NeelBhowmik/efficient-compact-fire-detection-cnn)

## Abstract:

_"In  this  work  we  investigate  the  automatic  detection  of  fire pixel  regions  in  video  (or  still)  imagery  within  real-time
bounds without reliance on temporal scene information.  As an extension to prior work in the field, we consider the performance  of  experimentally  defined,  reduced  complexity  deep convolutional neural network (CNN) architectures for this task. Contrary to contemporary trends in the field, our work illustrates
maximal accuracy of 0.93 for whole image binary fire detection (1),  with  0.89  accuracy  within  our  superpixel  localization
framework  can  be  achieved (2),  via  a  network  architecture  of significantly reduced complexity. These reduced architectures
additionally  offer  a  3-4  fold  increase  in  computational  performance offering up to 17 fps processing on contemporary
hardware  independent  of  temporal  infor

Excerpt of 17,504 characters

Read on GitHub

Top contributors5 shown

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

47/10047

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 25%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 95%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 8 years ago
Last push: 5 years ago
Last release: 7 years ago
Release tag: ICIP-2018
Releases in the last year: 0
Default branch: master
Size: 3.6k KB
Owner type: User
Owner location: UK
Discovered via: topic:computer-vision
First indexed: 14 days ago
Last synced: 9 days ago

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)

47MITPython

View on GitHub

Stars: 571
Forks: 173
Watchers: 571
Open issues: 3
Contributors: 5

Star history, last 90 days+1 over 7 snapshots

2026-07-24 · 5702026-08-06 · 571

Star history, last 90 days
Date	Stars
2026-07-24	570
2026-07-25	570
2026-07-28	569
2026-07-30	569
2026-07-31	570
2026-08-04	571
2026-08-06	571

Today

— stars today

This week

+2 stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.35%/day

From the README

# Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection

[and subsequent follow on work: _Experimental Exploration of Compact Convolutional Neural Network Architectures
for Non-temporal Real-time Fire Detection_]

![Python Build/Test](https://github.com/tobybreckon/fire-detection-cnn/workflows/Python%20Build/Test/badge.svg) Tested using Python 3.7.x, [TensorFlow 1.15](https://www.tensorflow.org/install/), [TFLearn 0.3.2](http://tflearn.org/) and [OpenCV 3.x / 4.x](http://www.opencv.org) (requires opencv extra modules - ximgproc module for superpixel segmentation)

## Architectures:
![FireNet](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/FireNet.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;FireNet architecture (above)
![InceptionV1-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV1-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV1-OnFire architecture (above)
![InceptionV3-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV3-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV3-OnFire architecture (above)
![InceptionV4-onFire](https://github.com/tobybreckon/fire-detection-cnn/blob/master/images/InceptionV4-OnFire.png)
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;InceptionV4-OnFire architecture (above)


## New Updated Architecture and Pytorch Models for Fire Detection available -- ![HERE](https://github.com/NeelBhowmik/efficient-compact-fire-detection-cnn)

## Abstract:

_"In  this  work  we  investigate  the  automatic  detection  of  fire pixel  regions  in  video  (or  still)  imagery  within  real-time
bounds without reliance on temporal scene information.  As an extension to prior work in the field, we consider the performance  of  experimentally  defined,  reduced  complexity  deep convolutional neural network (CNN) architectures for this task. Contrary to contemporary trends in the field, our work illustrates
maximal accuracy of 0.93 for whole image binary fire detection (1),  with  0.89  accuracy  within  our  superpixel  localization
framework  can  be  achieved (2),  via  a  network  architecture  of significantly reduced complexity. These reduced architectures
additionally  offer  a  3-4  fold  increase  in  computational  performance offering up to 17 fps processing on contemporary
hardware  independent  of  temporal  infor

Excerpt of 17,504 characters

Read on GitHub

Top contributors5 shown

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

47/10047

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 25%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 95%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 8 years ago
Last push: 5 years ago
Last release: 7 years ago
Release tag: ICIP-2018
Releases in the last year: 0
Default branch: master
Size: 3.6k KB
Owner type: User
Owner location: UK
Discovered via: topic:computer-vision
First indexed: 14 days ago
Last synced: 9 days ago

Top AI Repos — open-source AI, indexed and scored

tobybreckon/fire-detection-cnn

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

tobybreckon/fire-detection-cnn

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors5 shown

Quality score

What to know before adopting

Categories

Details