A RULE-BASED MACHINE VISION SYSTEM FOR FIRE DETECTION IN AIRCRAFT DRYBAYS AND ENGINE COMPARTMENTS

In this paper, a rule-based machine vision approach is applied to dete ct and categorize hydrocarbon fires in aircraft dry bays and engine co mpartments. Images for computer analysis are provided by charge-couple d device imaging sensors placed inside dry bays and engine compartment s. Using a set of heuristics based on statistical measures derived fro m the histogram and image subtraction analyses of successive image fra mes, we showed that it is possible to detect and categorize life-threa tening fires from non-fire/non-lethal events accurately in sub-millise cond response time. Specifically, the median, standard deviation, and first-order moment statistical measures of the histogram data of each image frame are used to confirm the presence or absence of fire. Concu rrently, another set of mean, median, and standard deviation statistic al measures from the image subtraction of two successive frames are us ed to determine the growth and subsequently reaffirm the existence of a fire. This approach is also tested for false alarms such as those du e to flashlights and high-power halogen lights. (C) 1997 Elsevier Scie nce B.V.