期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2013
卷号：6
期号：6
页码：309-320
DOI：10.14257/ijsip.2013.6.6.28
出版社：SERSC
摘要：Traditional smoke recognition based on HSI model or frame differentiation method can not reach the effect of real-time processing due to large amount of computation and requirement of too many images. A kind of automatic method for recognizing forest fire smoke based on gray bit plane aiming at to improve the real-time performance is proposed, analyze the gray information of forest fire smoke and use method combining gray bit plane with adaptive area of forest fire smoke, first, build gray bit plane of smoke image, and then calculate combining with the characteristics reflected by smoke information in each bit plane in order to improve the real-time performance and finally obtain the area of forest fire smoke. Experimental results show that the accuracy of recognizing area by analyzing and calculating gray bit plane is consistent with the traditional method, which takes a shorter time in processing and has actual application prospect to a certain degree.
关键词：Smoke recognition; Bit plane; Mean filtering; Automatic recognition
