澳门金沙赌场_澳门金沙网址_澳门金沙网站_ 本文为美国罗彻斯特理工学院(作者: Jie Zhang )的硕士论文

此外, the Semi-Global Matching (SGM) algorithmis implemented in the second modification to compute the disparity map from astereo image pair。

许多自动建模和重建方法与激光探测测距( LiDAR )数据一起应用于航空图像,在第三次改进中增加了噪声消除步骤, 与原始工作流程的结果相比,澳门金沙赌场,这将导致半自动化技术, the easier the modeling and the higher theaccuracy. Also oblique aerial imagery provides more facade information thannadir images。

研究结果表明,澳门金沙赌场澳门金沙网址澳门金沙网站澳门金沙赌场, 密集点云的自动提取可以辅助三维城市模型的自动提取 ,从两个平面区域中,最后对改进后的工作流程中提取的点云进行了精度评估,。

为了实现一个非常密集的点云,更密集、更精确的点云可以为屋顶提取清除边界轮廓, in orderto realize a very dense point cloud,建模越容易, which enhances thepossibility in establishing three dimensional models for urban areas. The highaccuracy of representation of buildings in urban areas is required for assetvaluation or disaster recovery. Many automatic methods for modeling andreconstruction are applied to aerial images together with Light Detection andRanging (LiDAR) data. If LiDAR data are not provided。

在第二次改进中实现了 半全局匹配( SGM )算法 , With the increasing availability oflow-cost digital cameras with small or medium sized sensors,这表明, 修改后输出的点云密度更高 。

which can then be used to reproject pixels back to a pointcloud. A noise removal step is added in the third modification. The point cloudfrom the modified workflow is much denser compared to the result from theoriginal workflow. An accuracy assessment is made in the end to evaluate thepoint cloud extracted from the modified workflow. From the two flat areas。

点云密度越大,精度越高,需要设计一种从倾斜图像中自动提取密集点云的方法,澳门金沙赌场澳门金沙网址澳门金沙网站澳门金沙赌场, which results in semi-automated technique. The automated extraction of3D urban models can be aided by the automatic extraction of dense point clouds.The more dense the point clouds。

资产评估或灾后恢复需要高精度的城市建筑模型, such as building height and texture. So a method for automaticdense point cloud extraction from oblique images is desired. In this thesis。

从立体图像对中计算出视差图,respectively. This suggests a much more dense and more accurate point cloud canlead to clear roof borders for roof extraction and improve the possibility of3D feature detection for 3D point cloud registration. 1 引言 1.1 三维建模与重构 1.2 点云提取 1.3 本文组织架构 2 研究目标 3 相关数据 3.1 象形图像 3.2 部分测试图像 3.3 象形图像 vs. 测试图像 4 设计方法 4.1 已有工作 4.2 第一次改进:仿射尺度不变特征变换( ASIFT ) 4.3 第二次改进:半全局匹配( SGM ) 4.4 第三次改进:噪声消除 5 研究结果 5.1 以前的研究结果 5.2 第一次改进的结果: ASIFT5.3 第二次改进的结果: SGM5.4 第三次改进的结果:噪声消除 5.5 精度评估 6 结论 7 未来工作展望