[1]陈以超 洪汉玉 王俊 张剑 王成刚.一种鲁棒性的遥感图像地域分类新方法[J].计算机技术与发展,2007,(08):136-139.
 CHEN Yi-chao,HONG Han-yu,WANG Jun,et al.A New Robust Approach for Remote Sensing Image Regional Classification[J].,2007,(08):136-139.
点击复制

一种鲁棒性的遥感图像地域分类新方法()
分享到:

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

卷:
期数:
2007年08期
页码:
136-139
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
A New Robust Approach for Remote Sensing Image Regional Classification
文章编号:
1673-629X(2007)08-0136-04
作者:
陈以超1 洪汉玉12 王俊1 张剑1 王成刚1
[1]武汉工程大学图像处理与智能控制实验室[2]华中科技大学图像识别与人工智能研究所
Author(s):
CHEN Yi-chao HONG Han-yu WANG Jun ZHANG Jian WANG Cheng-gang
[1]Lab. for Image Processing and Intelligent Control,Wuhan Inst. of Techn[2]Inst. for Pattern Recognition and Artificial Intelligence, Huazhong Univ. of Sci. and Techn
关键词:
遥感图像分类核密度估计非参数化特征空间重采样策略
Keywords:
remote sensing image classification kernel density estimation non-parameter feature space resampling strategy
分类号:
TP751
文献标志码:
A
摘要:
目前遥感图像分类算法面临的主要问题是分类精度与算法复杂度的矛盾及算法缺乏鲁棒性。为此,提出了一种基于特征空间重采样的非参数化核密度估计聚类与边缘检测相融合的多模型鲁棒性遥感图像分类方法。首先对遥感图像进行边缘检测以获取图像中每个像素的边缘梯度和方向信息;然后利用重采样策略,在联合域中对新的样本集合进行加权均值平移滤波,找到图像各区域的核密度函数局部最大值,通过迭代移动附近的数据点到此局部最大值;最后对各个分割区域进行合并,得到最终的分类图。实验结果表明,算法可获得高精度的遥感图像分类结果,且具有很强的鲁棒
Abstract:
The main problem of remote sensing image classification is the contradiction of classification precision and algorithm complexity, and algorithm lacking of robust. Therefore, a multi - model robust approach of remote sensing image classification based on non- parameter kernel density estimation of resampling strategy in feature space and edge detection is proposed in this paper. The edge gradient and direction information are obtained by edge detection of remote sensing. Then the new samples sets are weighted mean shift filtering to find kernd density function local maximum of image each region using resampling strategy in the joint spatial- range domain and data points are shifted the local maximum by iterative shifting. Last, the classification image is obtained by combining each region. Experimental results illustrate that it is able to classify remote sensing image effectively and robustly

相似文献/References:

[1]孙剑芬.基于高斯核密度估计的运动目标检测新方法[J].计算机技术与发展,2010,(08):45.
 SUN Jian-fen.New Method for Moving Object Detection Based on Gaussian Kernel Density Estimation[J].,2010,(08):45.
[2]熊开玲[],彭俊杰[],杨晓飞[],等. 基于核密度估计的K-means聚类优化[J].计算机技术与发展,2017,27(02):1.
 XIONG Kai-ling[],PENG Jun-jie[],YANG Xiao-fei[],et al. K-means Clustering Optimization Based on Kernel Density Estimation[J].,2017,27(08):1.
[3]马瑞新,郭芳清,刘振娇,等.融合上下文信息与核密度估计的协同过滤推荐[J].计算机技术与发展,2021,31(04):34.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 006]
 MA Rui-xin,GUO Fang-qing,LIU Zhen-jiao,et al.Collaborative Filtering Recommendation Algorithm for FusionContext Information and Kernel Density Estimation[J].,2021,31(08):34.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 006]

备注/Memo

备注/Memo:
国家自然科学基金项目(60572040);湖北省教育厅科学技术研究项目(D200615001)陈以超(1979-),男,湖北安陆人,硕士研究生,研究方向为遥感图像处理、数字图像分析;洪汉玉,博士后,教授,主要从事图像复原、自动目标识别和人工智能等方面的研究
更新日期/Last Update: 1900-01-01