Flame detection using HSI color space

作者: Buket Toptas , Davut Hanbay

DOI: 10.1109/IDAP.2017.8090322

关键词: Image processingGeographyColor gelComputer visionRGB color modelStage (hydrology)Mixture modelRemote sensingFlame detectionColor spaceColor analysisArtificial intelligence

摘要: Image processing based systems take important place in used to detect fires open spaces. Vision-based can spaces from distances and the fire at an early stage. In this study, a fire/flame detection method on color analysis of image is presented. The proposed consists three steps. First, RGB space converted HSI space. Then filter applied determine candidate zone. second stage, fake zones within zone identified as are eliminated. phase, difference gauss mixture model recover areas. third step, result two methods subjected AND processing. operation ensures exact flame As result, algorithm has been tested using video images. highest calculated accuracy 96%.

参考文章(0)