【作者】 黄雪青；

【导师】 李见为；

【作者基本信息】 重庆大学 ， 模式识别与智能系统， 2008， 硕士

【摘要】 随着高分辨率遥感影像的应用越来越普及,迫切要求人们对高分辨率遥感信息提取进行研究,以满足高分辨率遥感影像信息不断增长的应用和研究需要。然而,传统面向像元的分类方法在对高分辨率遥感影像进行分类时,存在着不能充分利用影像信息、分类精度降低、速度慢等局限性,根据高分辨率遥感影像的特点,本文提出面向对象的高分辨率遥感影像分类方法研究,在房屋提取实验中提出并使用了一种新的多尺度参数选择方法,提高了参数选择的速度。本文以深圳某地高分辨率遥感影像为例,选取具有典型特征的城区建筑物和高速公路以及地类丰富的区域的影像进行处理,以Ecognition软件为平台,对实验区进行面向对象的提取实验。首先,根据不同地物类型的特点,选取地物提取的最优分割尺度对实验区进行分割,构建地物类型提取的分类体系,提取地物类型的特征或特征组合,采用模糊分类法对地物类型进行分类,获得实验区的地物分类结果。最后将实验区面向对象遥感影像提取方法的提取结果与传统面向像元分类方法-最大似然分类法的分类结果进行对比评价,结果表明,采用面向对象遥感影像提取方法对高分辨率遥感影像进行信息提取时,提取的地物与真实地物具有较高的形状和属性一致性,提取的精度更高,提取结果也更易于理解和解释。更多还原

【Abstract】 With the application of the high-resolution remote sensing image more and more popular,it is urgently require people to carry on research to extraction of the high-resolution remote sensing in order to meet the increasing application and study requirement of the information of high-resolution images. However,when used the traditional pixel-oriented method to classify the high-resolution remote sensing image,it can’t fully utilize image information,should reduce the precision of classification and has slow speed. According to the characteristic of the high-resolution remote sensing image,the paper proposes to use the object-oriented method to classify high-resolution remotely sensed data. T paper uses a new method to determine the scale parameter in the extraction of house.. Enhances the speed of Determination.Taken the images of ShenZhen as an example,choosing the typical urban building area and high-way ,landuse abundant area as study areas,and regarding Ecognition software as the platform ,the paper carry on the classification experiment to study areas. First ,according to the characteristic of different surface features types ,choosing the optimum scale to segment the area to extract the object,constructing the classification system,extracting the characteristics or characteristic associations of the surface feature type,adopting the fuzzy classification to classify to surface types ,then getting the extraction result of study areas. At the end, the paper compares and appraises the extraction result between the method of object-oriented and pixel-oriented (the maximum likelihood classification). The result indicates that: the extracted surface features have higher shape and attribute consistency with true surface features when used object-oriented method; It has higher precision when used object-oriented method to classify the high-resolution image; The extraction result of object-oriented analysis is more easy to understand and explain.更多还原