[1]刘亮亮,谢菲,孟鸣.两种改进的遥感影像地物分类方法对比研究[J].计算机技术与发展,2018,28(02):154-157.[doi:10．3969/j．issn．1673－629X．2018．02．033]
　LIU Liangliang,XIE Fei,MENG Ming.A Comparative Study of Two Improved Remote Sensing Image Classification Methods[J].,2018,28(02):154-157.[doi:10．3969/j．issn．1673－629X．2018．02．033]
点击复制

两种改进的遥感影像地物分类方法对比研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
154-157
栏目:
应用开发研究
出版日期:
2018-02-10

文章信息/Info

Title:
A Comparative Study of Two Improved Remote Sensing Image Classification Methods
文章编号:
1673－629X(2018)02－0154－04
作者:
刘亮亮1; 谢菲1; 孟鸣1  2
1．云南大学 资源环境与地球科学学院，云南 昆明 650000;
2．云南省地理研究所，云南 昆明 650000
Author(s):
LIU Liang－liang1 ; XIE Fei1 ; MENG Ming1  2
1．School of Ｒesource Environment and Earth Science，Yunnan University，Kunming 650000，China;
2．Yunnan Institute of Geography，Kunming 650000，China
关键词:
贝叶斯分类; 影像分割; 特征提取; 小波变换; 海口镇
Keywords:
Bayesian classification; image segmentation; feature extraction; wavelet transform; Haikou Town
分类号:
TP301
DOI:
10．3969/j．issn．1673－629X．2018．02．033
文献标志码:
A
摘要:
遥感影像的分割中纹理特征是分辨、提取影像中地物类别的一个重要特征，文中提出一种利用贝叶斯公式进行遥感影像分类的思路，根据判断规则，选择改进概率最大的一个作为决策分类的结果。对比提出了另一种基于 Daubechies1 小波的改进 K －mean 算法影像分割技术，利用二维单尺度小波变换将图像像素分解到不同的维度空间，利用每个图像子块频带的平均能量值作为特征分量进行融合，最后利用小波逆变换还原分类图像。文中使用 MATLAB 2010a 软件进行算法实现，利用云南省滇池流域海口镇的 2015 年遥感影像数据进行了实验，最后对结果进行了定性分析和定量评价。结果表明，上述两种遥感影像分割算法在高分辨率遥感图像地物目标分类提取中取得较好的应用结果。
Abstract:
In the segmentation of remote sensing images，the texture feature is an important feature in the classification of the feature class．In this paper，we propose a method of using remote sensing image classification based on Bayesian formula．According to judgment rule，we choose the one with the greatest probability of improvement as the result of the decision classification．In contrast，an improved K －mean algorithm based on Daubechies1 wavelet is proposed．The two－dimensional single－scale wavelet transform is used to decompose the image pixels into different dimension spaces．The average energy value of each sub－block band of each image is used as a feature component for fusion．Finally，wavelet transform is used to restore the classified image．We implement the algorithm by MATLAB 2010a software，and carry out the experiment based on the remote sensing image data of Haikou Town，Dianchi Lake Basin，Yunnan Province．At last，the results are qualitative analysis and quantitative evaluation．The results show that two kinds of remote sensing image segmentation algorithm have a better effects in the object classification of high－resolution remote sensing image．

相似文献/References:

[1]张铮 高志森 李俊.改进贝叶斯分类算法在入侵检测中的研究[J].计算机技术与发展,2007,(01):174.
　ZHANG Zheng,GAO Zhi-sen,LI Jun.Research of Improved Bayesian Classification Arithmetic in Intrusion Detection[J].,2007,(02):174.
[2]黄越 臧冽 聂盼盼.一种混合分类方法的研究与改进[J].计算机技术与发展,2012,(05):48.
　HUANG Yue,ZANG Lie,NIE Pan-pan.Research and Improvement of One Combination of Multiple Classifiers[J].,2012,(02):48.
[3]周翔,方文俊,罗斌,等.基于血流模型和贝叶斯的红外人脸识别[J].计算机技术与发展,2013,(11):26.
　ZHOU Xiang[],FANG Wen-jun[],LUO Bin[],et al.Infrared Face Recognition Based on Blood Perfusion Model and Bayesian[J].,2013,(02):26.

更新日期/Last Update: 2018-03-29