COMPUTER VISION BASED FIRE DETECTION SOFTWARE

Conventional point smoke and fire detectors typically detect the presence of certain particles generated by smoke and fire by ionisation or photometry. Conventional sensors only aim to sense particles. An important weakness of point detectors is that they are distance limited and fail in open or large spaces. The strength of using video in fire detection is the ability to serve large and open spaces.

Below are some example screen-shots and videos of our fire, flame and smoke detection software.

Smoke Detection Sample Image

The image on the left shows an image with smoke and the image on the right shows detected smoke region.


 

Smoke Detection Sample Video

Click on the picture to play the smoke detection video.




Fire Detection Sample Image

The image on the left shows an image with fire and the image on the right shows detected fire region.

 
 

Fire Detection Sample Video

Click on the picture to play the fire detection video.




The fire and smoke detection system works in real-time by analyzing the video data captured by an ordinary surveillance camera and a frame grabber.

The software can be used in CCTV systems.

Computational complexity of the software is low.

The software is developed by Prof. A. Enis Cetin who is Associate Editor of IEEE Transactions on Image Processing.
Please contact him, if you are interested in this software.