首页 | 官方网站   微博 | 高级检索  
     

基于先验形状约束水平集模型的建筑物提取方法
引用本文:田昊,杨剑,汪彦明,李国辉.基于先验形状约束水平集模型的建筑物提取方法[J].自动化学报,2010,36(11):1502-1511.
作者姓名:田昊  杨剑  汪彦明  李国辉
作者单位:1.国防科学技术大学信息系统与管理学院 长沙 410073
摘    要:提出了一种先验形状约束的变分水平集模型, 并将其用于单幅遥感图像多建筑物的自动提取中. 将多个先验形状竞争模型引入水平集方法中, 在标记函数的指导下, 利用先验形状能量来约束曲线的演化, 在对图像进行分割的同时完成建筑物的检测和提取. 标记函数的引入, 加强了先验形状与要检测目标之间的匹配关系. 同时本文提出的模型具有先验形状的旋转、缩放和平移不变性. 最后的实验结果及定量定性的分析说明了本文方法的可行性.

关 键 词:水平集    先验形状    标记函数    建筑物检测    分割    变分方法
收稿时间:2009-11-2
修稿时间:2010-3-30

Towards Automatic Building Extraction: Variational Level Set Model Using Prior Shape Knowledge
TIAN Hao,YANG Jian,WANG Yan-Ming,LI Guo-Hui.Towards Automatic Building Extraction: Variational Level Set Model Using Prior Shape Knowledge[J].Acta Automatica Sinica,2010,36(11):1502-1511.
Authors:TIAN Hao  YANG Jian  WANG Yan-Ming  LI Guo-Hui
Affiliation:1.School of Information System and Management, National University of Defense Technology, Changsha 410073
Abstract:A novel variational level set model for multiple-building extraction from a single remote image is proposed in this paper. Multi-competing shapes are considered together with the level set model, the curve evolution is constrained by the prior shape knowledge and the label function which dynamically indicates the region with which the prior shape should be compared. The building extraction is addressed through a level set image segmentation approach that involves the use of the label function as well as the prior shape knowledge. In addition, the proposed model permits translation, scaling, and rotation of the prior shape. Experimental results and the qualitative and quantitative evaluations demonstrate the potential of the approach.
Keywords:Level sets  prior shape knowledge  label function  building detection  segmentation  variational method
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号