欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2014, Vol. 31 ›› Issue (5): 671-677.DOI: 10.7523/j.issn.2095-6134.2014.05.013

• 信息与电子科学 • 上一篇    下一篇

基于非线性形状先验的高分辨率遥感图像目标提取方法

刘格1,2,3, 胡岩峰1, 孙显1,2, 王宏琦1,2   

  1. 1. 中国科学院电子学研究所, 北京 100190;
    2. 中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190;
    3. 中国科学院大学, 北京 100190
  • 收稿日期:2013-10-17 修回日期:2014-01-13 发布日期:2014-09-15
  • 通讯作者: 刘 格,E-mail:liuge86@163.com
  • 基金资助:

    国家自然科学基金(61302170)和高分对地观测领域学术交流项目(GFZX04060103)资助

Nonlinear shape prior-based object extraction in high resolution remote sensing images

LIU Ge1,2,3, HU Yanfeng1, SUN Xian1,2, WANG Hongqi1,2   

  1. 1. Institute of Electronic, Chinese Academy of Sciences, Beijing 100190, China;
    2. Key Laboratory of Spatial Information Processing and Application System Technology, Chinese Academy of Sciences, Beijing 100190, China;
    3. University of Chinese Academy of Sciences, Beijing 100190, China
  • Received:2013-10-17 Revised:2014-01-13 Published:2014-09-15

摘要:

对已知目标形状,利用核主成分分析方法非线性建模,并根据高分辨率遥感图像特点,提出一种新的融入形状先验、图像边缘、颜色以及阴影信息的目标提取方法.该方法构造了基于活动轮廓模型的能量函数,并通过迭代的全局最优化方法最小化,实现对目标的准确分割提取.实验结果表明,该方法不仅能准确高效分割提取目标区域,而且能抵制背景噪声干扰,具有很强的鲁棒性和实用价值.

关键词: 目标分割提取, 形状先验, 活动轮廓模型, 全局最优化

Abstract:

In this study,given shape templates of some object,we model them by using kernel principal component analysis and then propose a new object extraction method for high resolution remote sensing images, which integrates shape prior and several image appearance information,including edge,color, and shadow. Based on active contour model,a new energy function is constructed and minimized through an iterative global optimization method to get the accurate segmentation results. Experimental results show that our method has high efficiency, high accuracy, and the robustness with respect to various background disturbances.

Key words: object extraction, shape prior, active contour model, global optimization

中图分类号: