基于多核支持向量机的高分辨率遥感影像建筑物提取研究-大地测量学与测量工程专业论文.docxVIP

Abst Abstract II III classification mathematical model that constructing by polynomial kernel function and radial basis function training to obtained classifier; finally, extract building through the training of MKSVM classifier. Compared the accuracy with the results of single-kernel SVM classification extraction buildings, relative to RBF kernel, two regions of MKSVM users classification precision is increased by about 1.5%, relatively to POLY kernel, two regions of MKSVM users classification precision is increased by about 3% to 5%; the Kappa coefficient of two regions is increased to 0.8579 and 0.8415, respectively. The experimental results show that, the operation of the image building information extraction system in this paper is reliable, object-oriented classification method based on MKSVM HYPERLINK /possess possesses higher accuracy when extracting buildings and better classification ability compared with single-kernel SVM extraction buildings. Key Words: Remote sensing image; Improved watershed segmentation; Mean shift segmentation; Impervious surface; Multi-kernel learning support vector machine; Building extraction 江西理 江西理工大学硕士学位论文 目录 目 录 摘 要 I Abstract II HYPERLINK \l _bookmark0 第一章 绪论 1 HYPERLINK \l _bookmark1 1.1 研究背景及研究意义 1 HYPERLINK \l _bookmark2 1.1.1 研究背景 1 HYPERLINK \l _bookmark3 1.1.2 研究意义 2 HYPERLINK \l _bookmark4 1.2 高分辨率遥感影像建筑物提取国内外研究现状 2 HYPERLINK \l _bookmark5 1.2.1 国外研究现状 3 HYPERLINK \l _bookmark6 1.2.2 国内研究现状 4 HYPERLINK \l _bookmark7 1.3 基于多核支持向量机分类的研究现状 5 HYPERLINK \l _bookmark8 1.4 论文的主要研究内容和技术路线 6 HYPERLINK \l _bookmark9 1.4.1 论文的主要研究内容 6 HYPERLINK \l _bookmark10 1.4.2 技术路线 7 HYPERLINK \l _bookmark11 1.5 论文结构安排 8 HYPERLINK \l _bookmark12 第二章 面向对象的遥感影像建筑物提取相关技术 9 HYPERLINK \l _bookmark13 2.1 影像分割技术 9 HYPERLINK \l _bookmark14 2.1.1 改进分水岭分割方法 9 HYPERLINK \l _bookmark15 2.1.2 均值漂移分割方法 11 HYPERLINK \l _bookmark16 2.2 高分辨