Automatic Change Detection in Synthetic Aperture Radar Images Based on PCANet

Gao, Feng; Dong, Junyu; Li, Bo; Xu, Qizhi

doi:10.1109/lgrs.2016.2611001

Cited by 225 publications

(137 citation statements)

References 14 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…For instance, Gong et al [33] designed an end-to-end deep neural network using a stack of restricted Boltzmann machine (RBM) and back propagation (BP) to produce change detection maps directly. Gao et al [34] proposed a semisupervised change detection model for synthetic aperture radar (SAR) images based on PCANet, in which training samples are obtained using Gabor wavelets and fuzzy cmeans. Zhang et al [35] presented a novel multi-spatialresolution change detection framework incorporating deeparchitecture-based unsupervised feature learning and mappingbased feature change analysis.…”

Section: B Deep Learning Based Change Detectionmentioning

confidence: 99%

From W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques

Hou

Liu

Wang

et al. 2020

IEEE Trans. Geosci. Remote Sensing

134

View full text Add to dashboard Cite

Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted features. Recently, the success of deep convolutional neural networks (CNNs) has widely spread across the whole field of computer vision for their powerful representation abilities. In this paper, we therefore address the remote sensing image change detection problem with deep learning techniques. We firstly propose an end-to-end dual-branch architecture, termed as the W-Net, with each branch taking as input one of the two bi-temporal images as in the traditional change detection models. In this way, CNN features with more powerful representative abilities can be obtained to boost the final detection performance. Also, W-Net performs differencing in the feature domain rather than in the traditional image domain, which greatly alleviates loss of useful information for determining the changes. Furthermore, by reformulating change detection as an image translation problem, we apply the recently popular Generative Adversarial Network (GAN) in which our W-Net serves as the Generator, leading to a new GAN architecture for change detection which we call CDGAN. To train our networks and also facilitate future research, we construct a large scale dataset by collecting images from Google Earth and provide carefully manually annotated ground truths. Experiments show that our proposed methods can provide fine-grained change detection results superior to the existing state-of-the-art baselines.

show abstract

Section: B Deep Learning Based Change Detectionmentioning

confidence: 99%

From W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques

Hou

Liu

Wang

et al. 2020

IEEE Trans. Geosci. Remote Sensing

134

View full text Add to dashboard Cite

show abstract

“…The PCA-Net was first proposed [14] for image classification and, then, applied to SAR image change detection [15]. The main difference from convolution neural network is that the filter kernels in the PCA-Net are obtained without back-propagation, which reduces computation complexity.…”

Section: A Pca Network For Sar Image Change Detectionmentioning

confidence: 99%

“…The proposed method (PCA-Net-buc) is compared with the PCA-Net trained by pseudolabels [15] (PCA-Net) and the supervised PCA-Net trained with the samples only randomly drawn from changed and unchanged regions (PCA-Net-uc). In addition, we also compared the proposed method with the DNN [12].…”

Section: A Experiments Configuresmentioning

confidence: 99%

See 1 more Smart Citation

Imbalanced Learning-Based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net

Wang

Zhang

Chen

et al. 2019

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Change detection is a quite challenging task due to the imbalance between unchanged and changed class. In addition, the traditional difference map generated by log-ratio is subject to the speckle, which will reduce the accuracy. In this letter, an imbalanced learning-based change detection is proposed based on PCA network (PCA-Net), where a supervised PCA-Net is designed to obtain the robust features directly from given multitemporal synthetic aperture radar (SAR) images instead of a difference map. Furthermore, to tackle with the imbalance between changed and unchanged classes, we propose a morphologically supervised learning method, where the knowledge in the pixels near the boundary between two classes is exploited to guide network training. Finally, our proposed PCA-Net can be trained by the data sets with available reference maps and applied to a new data set, which is quite practical in change detection projects. Our proposed method is verified on five sets of multiple temporal SAR images. It is demonstrated from the experiment results that with the knowledge in training samples from the boundary, the learned features benefit change detection and make the proposed method outperform than supervised methods trained by randomly drawing samples.

show abstract

“…Ternary here refers to classifying pixels to the positive change, negative change, and unchanged. Gao et al, (2016) utilized a kind of deep neural network, PCANet, for change detection of radar images. Firstly, FCM clustering and Gabor wavelets were applied to find pixels with a high probability of being changed and unchanged.…”

Section: Introductionmentioning

confidence: 99%

A Convolutional Neural Network for Flood Mapping Using Sentinel-1 and SRTM Dem Data: Case Study in Poldokhtar-Iran

Hosseiny

Ghasemian

Amini

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Flood contributes a key role in devastating natural and man-made areas. Floods usually are occurred when there is a considerable number of clouds in the sky making optic data useless. Synthetic aperture radar (SAR) images can be a valuable data source in earth observation tasks. The most important characteristic of the radar image is its ability to penetrate the cloud and dust. Therefore, monitoring earth in cloudy or rainy weather can be available by this kind of dataset. In the last few years by improving machine learning methods and development of convolutional neural networks in remote sensing applications we are facing with extremely high improvement in classification tasks. In this paper, we use dual-polarized VV and VH backscatter values of Sentinel-1 and Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) dataset in a proposed convolutional neural network to generate a land cover map of a flooded area before and after happening. Obtained classification results vary between 93.3% to 98.5% for different training sizes. By comparing the generated classified maps, flooded areas of each class can be extracted.

show abstract

Automatic Change Detection in Synthetic Aperture Radar Images Based on PCANet

Cited by 225 publications

References 14 publications

From W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques

From W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques

Imbalanced Learning-Based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net

A Convolutional Neural Network for Flood Mapping Using Sentinel-1 and SRTM Dem Data: Case Study in Poldokhtar-Iran

Contact Info

Product

Resources

About