Anew hybrid algorithm for fire vision recognition inside the closed rooms in the nuclear reactor of Eygpt

Abstract EN

A novel method to detect fire and / or smoke in real-time is introduced.

The objective of this work is recognizing and modeling fire shape evolution in stochastic visual phenomenon.

It focuses on detection of fire in image sequences by applying a new hybrid algorithm that depends on adapting the back-propagation algorithm, using a new adaptive terminal attractor algorithm, after canny edge detection, for determining the smoke and fire boundaries.

Another clue detects smoke and fire flicker by analyzing the video in the wavelet domain.

Color variations in flame regions are detected by computing the spatial wavelet transform of moving fire-colored regions.

An uncontrolled fire in a nuclear facility can be a very energetic event.

The new hybrid is applied for real time fire recognition in the rooms of the second nuclear reactor of Egypt, which have high radiation levels.

Experimental results show that the proposed algorithm is very successful in detecting fire and / or smoke in a small real time.