Particle Detection and Classification in Photoelectric Smoke Detectors Using Image Histogram Features

Abstract

Due to the failure of detecting smaller smoke particles (<; 1 nm in diameter) and the occurrence of false positives by commercially available photoelectric smoke detectors, a new detection algorithm was constructed by analyzing the image histogram features of smoke particles generated by Rayleigh scattered light to detect and classify the smoke particles of common household fires. Seven particle types were selected and exposed to a continuous spectrum of light in a closed particle chamber and a significant result was achieved over the common photoelectric smoke detectors by detecting all test particles using colour histograms. As Rayleigh theory suggested, comparing the intensities of scattered light of different wavelengths is the best method to classify different sized particles. Existing histogram comparison methods based on histogram bin values failed to evaluate a relationship between the scattered intensities of individual red, green and blue laser beams with different sized particles due to the uneven particles movements inside the chamber. The proposed classification algorithm which is based on a particle density independent feature, histogram maximum value index, classified all the monotype particles with 100% accuracy. As expected, the classifier failed to distinguish wood smoke from other monotype particles since wood smoke is itself a complex composition of many monotype particles.