Habiboğlu, Y. HakanGünay, OsmanÇetin, A. Enis2016-02-082016-02-0820112219-5491http://hdl.handle.net/11693/28306Date of Conference: 29 Aug.-2 Sept. 2011A video based wildfire detection system that based on spatio-temporal correlation descriptors is developed. During the initial stages of wildfires smoke plume becomes visible before the flames. The proposed method uses background subtraction and color thresholds to find the smoke colored slow moving regions in video. These regions are divided into spatio-temporal blocks and correlation features are extracted from the blocks. Property sets that represent both the spatial and the temporal characteristics of smoke regions are used to form correlation descriptors. An SVM classifier is trained and tested with descriptors obtained from video data containing smoke and smoke colored objects. Experimental results are presented. © 2011 EURASIP.EnglishBackground subtractionCorrelation featuresDescriptorsInitial stagesMoving regionsSmoke plumeSpatio-temporalSpatiotemporal correlationSVM classifiersTemporal characteristicsVideo dataWildfire detectionFiresSignal processingSmokeConference Paper