基于GSO-SVM的高分辨率遥感影像分类方法  

Classification Method of High Resolution Remote Sensing Images Based on GSO-SVM

作　　者：李宇国 LI Yuguo(Land Reserve Center of Sihui City,Zhaoqing 526200,China)

机构地区：[1]广东省四会市土地储备中心,广东四会526200

出　　处：《江西测绘》2024年第4期20-22,30,共4页JIANGXI CEHUI

摘　　要：为了实现高分辨率遥感影像的精准分类,论文设计了一种基于萤火虫(GlowwormSwarmOptimization,GSO)算法优化支持向量机(SupportVectorMachine,SVM)的高分辨率遥感影像分类方法,采用GSO算法对SVM参数最优值进行搜索,构建了GSO-SVM模型。利用实际拍摄的高分辨率遥感影像进行仿真实验,并将GSO-SVM模型的分类结果与SVM模型和BP神经网络模型进行对比,结果表明,GSO-SVM模型遥感影像分类结果的综合分类精度为87.5%,Kappa系数为0.8338,分类效果更好,验证了GSO-SVM模型的有效性。In order to accurately classify high-resolution remote sensing images,this paper proposes a method based on the Glowworm Swarm Optimization(GSO)algorithm to optimize Support Vector Machine(SVM).The GSO algorithm is used to search for the optimal values of SVM parameters and a GSO-SVM model is constructed.Simulation experiments are conducted using actual high-resolution remote sensing images,and the classification results of the GSO-SVM model are compared with the SVM model and the BP neural network model.It shows that the comprehensive classification accuracy of the remote sensing image classification results by GSO-SVM model is 87.5%,and the Kappa coefficient is 0.8338.The classification effect is better,which verifies the effectiveness of the GSO-SVM model.

关 键 词：遥感图像 分类 萤火虫算法优化 支持向量机 

分 类 号：P237[天文地球—摄影测量与遥感]