A Novel Approach for Hyperspectral Change Detection Based on Uncertain Area Analysis and Improved Transfer Learning

A Novel Approach for Hyperspectral Change Detection Based on Uncertain Area Analysis and Improved Transfer Learning
复制标题

基于不确定区域分析和改进迁移学习的高光谱变化检测新方法

DOI:
10.1109/jstars.2020.2990481
复制
发表时间:
2020-04
影响因子:
5.5
通讯作者:
Xu Xiong
Xu Xiong
中科院分区:
工程技术3区
文献类型:
--
作者:
Tong Xiaohua;Pan Haiyan;Liu Sicong;Li Binbin;Luo Xin;Xie Huan;Xu Xiong

文献摘要

参考文献

被引文献

相似文献

虽然在过去的几年中已经提出了一些变化检测(CD)的方法,他们中的大多数是基于假设,有训练样本或没有训练样本的pretime和posttime图像。很少有研究已经解决了只有少量的训练样本,只有在一个单一的时间图像。在这篇文章中,我们提出了一种新的方法,可以检测多个变化的双时高光谱图像时,只有几个训练样本中的一个图像(源图像)。该方法包括四个主要步骤:第一,基于不确定区域分析的无监督CD生成二值变化图;第二,根据主动学习对源图像(X1)进行分类;第三,使用改进的迁移学习对目标图像(X2)进行分类;第四,通过分类后比较生成多类变化图。该方法在一个模拟数据集和两对真实的双时相高光谱图像上进行了测试。实验结果表明:首先,不确定区域分析可以提高二值CD的准确率;而主动学习和改进的迁移学习可以提高源图像和目标图像的分类准确率,使用所提出的方法可以提高多CD的准确率;其次,与现有方法相比,所提出的方法产生了最好的结果。
Although a number of change detection (CD) methods have been proposed during the past years, most of them are developed based on the assumption that there are either training samples or no training samples for both the pretime and posttime images. Few studies have addressed the scenario of only small amounts of training samples are available only in a single-time image. In this article, we propose a novel approach that can detect multiple changes in bitemporal hyperspectral images when only a few training samples are available in one of the images (the source image). The proposed method consists of four main steps: first, unsupervised CD based on uncertain area analysis to generate the binary change map; second, classification of the source image (X1) according to active learning; third, classification of the target image (X2) by the use of improved transfer learning; and fourth, generation of the multiclass change map by postclassification comparison. The proposed method was tested on one simulated dataset and two pairs of real bitemporal hyperspectral images. Experimental results demonstrate that: first, uncertain area analysis can improve the binary CD accuracy; while active learning and improved transfer learning can enhance the classification accuracy of the source and target images, the multiple CD accuracy is increased by the use of the proposed method; and second, compared with the state-of-the-art methods, the proposed method produced best results.
DOI: 10.1016/j.isprsjprs.2006.09.004
发表时间: 2006-11
影响因子: 12.7
作者:
H. Nemmour;Y. Chibani
通讯作者: H. Nemmour;Y. Chibani
基于子空间的高光谱图像变化检测方法
DOI: 10.1109/jstars.2013.2241396
发表时间: 2013-02
影响因子: 5.5
作者:
Wu, Chen;Du, Bo;Zhang, Liangpei
通讯作者: Zhang, Liangpei
DOI: 10.1016/j.isprsjprs.2015.02.004
发表时间: 2015-09
影响因子: 12.7
作者:
Z. Qi;A. Yeh;Xia Li;Xiaohu Zhang
通讯作者: Z. Qi;A. Yeh;Xia Li;Xiaohu Zhang
DOI: --
发表时间: 2012-12
期刊: --
影响因子: --
作者:
Quanquan Gu;Tong Zhang;C. Ding;Jiawei Han
通讯作者: Quanquan Gu;Tong Zhang;C. Ding;Jiawei Han
DOI: 10.1016/j.rse.2004.04.001
发表时间: 2004-06
影响因子: 13.5
作者:
S. L. Hégarat-Mascle;R. Seltz
通讯作者: S. L. Hégarat-Mascle;R. Seltz