遥感影像亚像元定位研究综述

Sub-pixel mapping of remotely sensed imagery:a review

遥感影像亚像元定位是在混合像元分解基础上,利用地物空间分布特征确定不同地物类型在混合像元中的具体位置,得到亚像元尺度的地物分类图,是一种有效解决混合像元空间不确定性的方法。首先介绍遥感影像亚像元定位的基本概念,分析亚像元定位的理论模型和求解算法;然后总结亚像元定位模型的误差来源、精度评价方法以及结果不确定性的表达手段,同时讨论利用辅助数据源提高亚像元定位精度的主要方法;最后对亚像元定位的研究趋势做了进一步展望。

Sub-pixel mapping of remotely sensed imagery is a post-processing method of pixel unmixing in order to solve the issue of spatial uncertainty of mixed pixels. With the fraction images derived from pixel unmixing technologies as input, the spatial distribution of each land cover class within mixed pixels is determined and a sub-pixel scale land cover map is generated according to the spatial correlation principle. This paper firstly introduces the concept of sub-pixel mapping and analyses the theoretial models and currently used algorithms. Then, the main sources of errors, different accuracy assessments of the model and the ways to present the uncertainty of the model are summarized. The main methods for increasing the accuracy of sub-pixel mapping by ancillary data are also discussed. Finally, this paper concludes with an outlook and several key techniques of sub-pixel mapping.