6 February 2012 Wildfire smoke detection using temporospatial features and random forest classifiers
Author Affiliations +
Abstract
We propose a wildfire smoke detection algorithm that uses temporospatial visual features and an ensemble of decision trees and random forest classifiers. In general, wildfire smoke detection is particularly important for early warning systems because smoke is usually generated before flames; in addition, smoke can be detected from a long distance owing to its diffusion characteristics. In order to detect wildfire smoke using a video camera, temporospatial characteristics such as color, wavelet coefficients, motion orientation, and a histogram of oriented gradients are extracted from the preceding 100 corresponding frames and the current keyframe. Two RFs are then trained using independent temporal and spatial feature vectors. Finally, a candidate block is declared as a smoke block if the average probability of two RFs in a smoke class is maximum. The proposed algorithm was successfully applied to various wildfire-smoke and smoke-colored videos and performed better than other related algorithms.
© 2012 Society of Photo-Optical Instrumentation Engineers (SPIE)
Byoung Chul Ko, Joon-Young Kwak, Jae-Yeal Nam, "Wildfire smoke detection using temporospatial features and random forest classifiers," Optical Engineering 51(1), 017208 (6 February 2012). https://doi.org/10.1117/1.OE.51.1.017208 . Submission:
JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top