论文部分内容阅读
全球变化研究需要将多种传感器光谱波长接近的图像波段一起使用,以满足遥感应用对时间分辨率和区域覆盖的要求,这给遥感图像处理提出了新要求,涉及多传感器多时相数据几何定位一致性问题、辐射归一化问题及地类属性标识一致性问题以及高度自动化处理的问题。针对上述几方面问题,提出了一个基于“不变特征点集”IFPs(Invariant Feature Points set)作为控制数据集的区域级遥感图像自动化处理框架,将图像的几何空间、辐射值空间和类别属性值空间的时空对齐问题纳入到统一框架,提供了一种间接快速处理的手段和理念,并对构建IFPs的关键技术进行了综述。
Global change research requires the use of a variety of sensor spectral wavelengths near the image band together to meet the remote sensing applications of time resolution and regional coverage requirements, which put forward new requirements for remote sensing image processing, involving multi-sensor multi-phase data consistent geometric positioning Sexual problems, radiation normalization problems and land-use attribute identification consistency problems, as well as highly automated processing problems. In order to solve the above problems, this paper proposes a frame-level remote sensing image processing framework based on “Invariant Feature Points Set ” (IFPs) as the control dataset. The geometric space, radiation space and category Spatial-temporal alignment of attribute value space into the unified framework provides an indirect means of rapid processing and ideas, and the key technologies for the construction of IFPs are reviewed.