关键词: 星载高分辨率图像, 建筑物高度, 大面积, 快速提取, 形态学阴影指数, 模型匹配法, 线性回归

Abstract: The spaceborne high-resolution optical images and synthetic aperture radar (SAR) images are applied to extract building height in urban areas widely. But the lack of optical satellite parameters along with the SAR images' incomplete scattering characteristics and inefficient extraction make the application flawed. To cure the above problems, we investigated the joint use of the spaceborne high-resolution optical images and SAR images to extract building height information quickly in big urban areas. The chain is decomposed into the main following steps: First, the building shadows are extracted by integrating support vector machines (SVM) with morphological shadow index (MSI) and their lengths are measured automatically. Then, the height extraction from SAR images based on a model matching technique for some appropriate samples. Finally, obtain the other heights based on the simple linear regression analysis. This approach which combines the data and feature from different satellite systems to make up the flaws for each other is not only efficient and low-cost, but also satisfy the basic accuracy requirement.

Key words: spaceborne high-resolution image, building height, big areas, quick extraction, MSI, model match technique, simple linear regression