文献类型：期刊文献

中文题名：基于蚁群优化与独立特征集的遥感图像实时分类算法

英文题名：Real-time classification algorithm of remote sensing images based on ant colony optimization algorithm and independent feature sets

作者：赵芳[1];索岩[2];彭子然[3]

第一作者：赵芳

机构：[1]新乡学院计算机与信息工程学院,河南新乡453003;[2]河南师范大学新联学院,河南新乡453000;[3]中南大学信息科学与工程学院,长沙410083

第一机构：新乡学院计算机与信息工程学院

年份：2020

卷号：0

期号：2

起止页码：573-577

中文期刊名：计算机应用研究

外文期刊名：Application Research of Computers

收录：CSTPCD;;北大核心:【北大核心2017】；CSCD:【CSCD_E2019_2020】；

基金：国家自然科学基金资助项目(61272121);河南省科技攻关计划项目(172102210445).

语种：中文

中文关键词：人工智能;特征提取;遥感图像;时间效率;蚁群优化算法;极限学习机

外文关键词：artificial intelligence;feature abstraction;remote sensing image;computational efficiency;ant colony optimization algorithm;extreme learning machine

摘要：为了提高遥感图像的实时分类准确率与效率,提出了一种基于蚁群优化算法与独立特征集的遥感图像集实时分类算法。首先,提取遥感图像的小波域特征与颜色特征,并且组成特征向量;然后,采用蚁群优化算法对特征空间进行优化,独立地选出每个分类的显著特征集,从而降低每个子特征空间的维度;最终,每个分类独立地训练一个极限学习机分类器,从而实现对遥感图像集的分类。基于公开的遥感图像数据集进行了仿真实验,结果显示本算法实现了较高的分类准确率,并且实现了较高的计算效率。
In order to improve the accuracy and efficiency of real-time classification of remote sensing images,this paper proposed a real-time classification algorithm of remote sensing images based on the ant colony optimization algorithm and independent feature sets.Firstly,it abstracted wavelet features and color features of remote sensing images,and the features formed the feature vectors.Then,it adopted the ant colony optimization algorithm to optimize the feature space,and it selected the significant feature set of each class independently to reduce the dimension of each feature sub-space.Lastly,it trained extreme learning machine for each class independently to realize the remote sensing images classification.Simulation experimental results based on the public remote sensing image dataset show that the proposed algorithm realizes a good classification accuracy and computational efficiency.