一种利用影像匹配的城区三维景观图生成途径

A Landscape Map Generation Method Based on Image Matching

提出了一种基于影像匹配的城区三维景观图生成方法，它首先利用神经网络影像匹配得出城区的密集视差表面，再利用基于模板匹配的半自动建筑物提取方法获得建筑物的关量数据和高程，进而得出城区三维数字模型，从而获得真实的城区三维透视景观图。

This paper describes an integrated approah to the construction of textured 3D scene medel of buildings from digital images. This approah is implemented in a colection of the global image maching and least Square template matching algorithnis. At first, we use improved global iInag matching algorithm had on variable weight srnooth constraint to get the dense disparity surfaC of the city and the height of every building. Then use a semi-automatic algorithm based on least Square ternplate matching to get the accrete edg of buildings. In this approah, the operator recognizes the building and give an approximate location of it in an active mode.The template matching approach autotnaically searhes the exact location of the building's edge. Through this step,we get the vector data of every building in image. At last, we combine both the vector data and texture data in images to reconstruct the textured landscaPe of the buildings. The potential application include create reality medel to be used in city areas and mapping in city area semi-automaically.