期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2012
卷号：46
期号：1
页码：207-211
出版社：Journal of Theoretical and Applied
摘要：In order to determine the forest fire danger rating quickly while finding it during the aviation of forest protection, it is important to calculate the fire area. Until recently the area has been mostly calculated by people�s experience. With the mature of digital image processing technology, an assumption based on the forest fire area calculation of aerial images has been made, and the key point is how to identify and extract the fire area. In this paper, a extraction method on forest fire area based on the combination of color and gray level information has been proposed. First, the adaptive threshold should be found by applying the Otsu threshold method to a gray image. Then, the image analysis should be made by the RGB space component�s characteristics of the target images� color features. Compared with traditional image segmentation methods, experiments show that the proposed method has low false points rate, good area consistency, accurate and clear edge, and can be used to extract and segment the fire area of aerial images.
关键词：Forest Fire; Aerial Image; Image Segmentation; Fire Area Extraction
