作者: Feng Ling , Wenbo Li , Yun Du , Xiaodong Li
DOI: 10.1109/LGRS.2010.2055034
关键词:
摘要: Extracting land cover change (LCC) information at the subpixel scale is important when coarse-resolution remotely sensed images are used for detection. Although fraction derived from soft-classification technologies can be LCC detection, spatial distribution of changed subpixels within each pixel cannot provided. This letter presents a mapping (SLCCM) algorithm, aiming to predict pattern between bitemporal through comparing former high-resolution map and latter image. The resulting determined by dependence principle an rule in mixed pixel. proposed algorithm was evaluated with simulated real images, results showed effectiveness method SLCCM.