Multi-class change detection of remote sensing images based on class rebalancing  

作　　者：Huakang Tang Honglei Wang Xiaoping Zhang 

机构地区：[1]School of Electrical Engineering,Guizhou University,Guiyang,People’s Republic of China [2]Key Laboratory of “Internet+” Collaborative Intelligent Manufacturing,Guizhou Province,Guiyang,People’s Republic of China [3]Science and Technology Department,Guizhou Province,Guiyang,People’s Republic of China

出　　处：《International Journal of Digital Earth》2022年第1期1377-1394,共18页国际数字地球学报（英文）

基　　金：supported by Guizhou Science and Technology Cooperation Program:[Grant Number QKH[2016]5103].

摘　　要：Multi-class change detection can make various ground monitoring projects more efficient and convenient.With the development of deep learning,the multi-class change detection methods have introduced Deep Neural Network(DNN)to improve the accuracy and efficiency of traditional methods.The class imbalance in the image will affect the feature extraction effect of DNN.Existing deep learning methods rarely consider the impact of data on DNN.To solve this problem,this paper proposes a class rebalancing algorithm based on data distribution.The algorithm iteratively trains the SSL model,obtains the distribution of classes in the data,then expands the original dataset according to the distribution of classes,and finally trains the baseline SSL model using the expanded dataset.The trained semantic segmentation model is used to detect multi-class changes in two-phase images.This paper is the first time to introduce the image class balancing method in the multi-class change detection task,so a control experiment is designed to verify the effectiveness and superiority of this method for the unbalanced data.The mIoU of the class rebalancing algorithm in this paper reaches 0.4615,which indicates that the proposed method can effectively detect ground changes and accurately distinguish the types of ground changes.

关 键 词：Multi-class change detection remote sensing class rebalancing semantic segmentation 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]