Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (24): 170-172.DOI: 10.3778/j.issn.1002-8331.2009.24.050

• 图形、图像、模式识别 • Previous Articles     Next Articles

Non-parametric multiphase level set method for remote sensing image classification

LIN Ying1,YIN Gui-sheng1,YANG Yun2   

  1. 1.College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China
    2.College of Geology Engineering and Geomatics,Chang’an University,Xi’an 710054,China
  • Received:2009-05-13 Revised:2009-07-03 Online:2009-08-21 Published:2009-08-21
  • Contact: LIN Ying

非参多水平集遥感图像分类方法

林 颖1,印桂生1,杨 耘2   

  1. 1.哈尔滨工程大学 计算机学院,哈尔滨 150001
    2.长安大学 地质工程与测绘学院,西安 710054

  • 通讯作者: 林 颖

Abstract: The characteristics of spectral variations and details disturbances bring great disadvantages to remote sensing image classification.To solve the problem,this paper presents a novel multi-phase level set method based on non-parametric density estimation technique.Firstly,Parzen window non-parametric density estimation technique is introduced into the level set framework so as to improve accuracy of probability density estimation.In addition,a new energy term is introduced using textures derived from Gabor filter,in order to strengthen texture analysis of multi-spectral imagery.Experimental comparisons and analysis show that the proposed model performs an effectiveness of alleviating those problems mentioned above,in the case of little priori knowledge of study area.

Key words: multispectral image classification, multiphase level set, Parzen window, density estimation, spectral inhomogeneity

摘要: 多光谱影像中存在着光谱异质性、细节干扰及地物拓扑结构复杂等特点,给遥感分类带来诸多不利影响。针对此类问题,提出一种新的非参数密度估计的多水平集分类方法:将Parzen窗非参数密度估计方法集成到多相位水平集框架中,用以提高复杂场景中样本概率密度估计的准确性,并增强抗干扰能力;此外,基于Gabor小波滤波器导出的纹理特征构造了一个新的能量项以增强模型的纹理分析能力。实验对比及分析验证了所提出的模型在仅有少量先验知识的条件下,可有效地改善遥感图像分类的质量。

关键词: 多光谱图像分类, 多相位水平集, Parzen窗, 密度估计, 光谱异质

CLC Number: