Feature learning and change feature classification based on deep learning for ternary change detection in SAR images
Feature learning and change feature classification based on deep learning for ternary change detection in SAR images
复制标题
DOI：
10.1016/j.isprsjprs.2017.05.001
复制
发表时间：
2017-07-01
影响因子：
12.7
通讯作者：
Zhang, Puzhao
中科院分区：
文献类型：
--
作者：
Gong, Maoguo;Yang, Hailun;Zhang, Puzhao
三元变化检测的目的是检测变化，并将变化分为积极变化和消极变化。这对于时空合成孔径雷达图像的联合解译具有重要意义。本文将稀疏自动编码器、卷积神经网络(CNN)和无监督聚类相结合来解决无监督的三值变化检测问题。首先，使用稀疏自动编码器将对数比差图像变换到合适的特征空间，以提取密钥变化并抑制孤立点和噪声。然后将学习到的特征聚为三类，作为伪标签训练CNN模型作为变化特征分类器。CNN的可靠训练样本是从稀疏自动编码器学习的特征图中按照一定的选择规则选择出来的。有了训练样本和相应的伪标签，CNN模型就可以通过随机梯度下降的反向传播来训练。在其训练过程中，CNN被驱动学习变化的概念，并建立了更强大的模型来区分不同类型的变化。与传统方法不同，该框架结合了稀疏自动编码器和CNN的优点，学习了更稳健的差分表示和变化的概念，用于三值变化检测。在真实数据集上的实验结果验证了该框架的有效性和优越性。(C)2017年国际摄影测量和遥感学会(摄影测量和遥感学会)。爱思唯尔出版，版权所有。
Ternary change detection aims to detect changes and group the changes into positive change and negative change. It is of great significance in the joint interpretation of spatial-temporal synthetic aperture radar images. In this study, sparse autoencoder, convolutional neural networks (CNN) and unsupervised clustering are combined to solve ternary change detection problem without any supervison. Firstly, sparse autoencoder is used to transform log-ratio difference image into a suitable feature space for extracting key changes and suppressing outliers and noise. And then the learned features are clustered into three classes, which are taken as the pseudo labels for training a CNN model as change feature classifier. The reliable training samples for CNN are selected from the feature maps learned by sparse autoencoder with certain selection rules. Having training samples and the corresponding pseudo labels, the CNN model can be trained by using back propagation with stochastic gradient descent. During its training procedure, CNN is driven to learn the concept of change, and more powerful model is established to distinguish different types of changes. Unlike the traditional methods, the proposed framework integrates the merits of sparse autoencoder and CNN to learn more robust difference representations and the concept of change for ternary change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed framework. (C) 2017 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.