基于中心聚类的深度学习遥感图像场景分类方法  

Deep Learning Remote Sensing Image Scene Classification Method Based on Central Clustering

作　　者：廖建平[1] LIAO Jianping(School of Information Engineering,Quzhou College of Technology,Quzhou 324000,China)

机构地区：[1]衢州职业技术学院信息工程学院教务处,浙江衢州324000

出　　处：《现代信息科技》2021年第10期27-29,33,共4页Modern Information Technology

基　　金：浙江省教育厅科研项目(Y201941374)。

摘　　要：针对遥感影像场景分类提出一种改进的中心聚类的深度学习模型,该模型通过改进不同类型特征的距离间隔,提高遥感图像场景分类的性能。与现有其他深度学习模型相比,该模型通过添加聚类中心以及特征与聚类中心的距离间隔约束,设计新的目标函数。新目标函数由交叉熵损失和中心聚类间隔损失构成。通过在两个公共基准数据集上评估所提出的目标函数,分类结果获得明显提升。For remote sensing image scene classification,an improved central clustering deep learning model is proposed,which improves the performance of remote sensing image scene classification by improving the distance interval of different types of features.Compared with other existing deep learning models,this model designs a new objective function by adding cluster center and the distance interval constraint between feature and cluster center.The new objective function consists of cross entropy loss and central clustering interval loss.By evaluating the proposed objective function on two common benchmark datasets,the classification results are significantly improved.

关 键 词：遥感图像 中心聚类 深度学习 卷积神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]