Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery

Su, Hang; Zhang, Xinzheng; Luo, Yuqing; Zhang, Ce; Zhou, Xichuan; Atkinson, Peter M.

doi:10.1016/j.isprsjprs.2022.09.006

Cited by 9 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ratios of changed to unchanged pixels in the reference data for Data A, B, C, D, and E are 0.22, 0.14, 0.30, 0.29, and 0.34, respectively. In addition, similar to some remote sensing image analysis methods based on GNNs, we selected some of the nodes as the training set and the rest as the test set [16,[88][89][90]. For Data A, B, C, D, and E, the division ratios of the training set and test set were 300:10579, 200:7806, 3001: 2871, 300:9805, and 400:17589, respectively.…”

Section: Semi-supervised Learningmentioning

confidence: 99%

“…Second, 86 with the image objects as nodes, an adjacent matrix was 87 established to construct a multitemporal image network. 88 Then, we used the chi-square transformation (CST) to 89 calculate the weighted difference of the multidimensional 90 features, and the weighted difference similarity matching 91 method (WDSM) was used to improve the graph connection 92 density. Moreover, the Siamese autoencoder was used to 93 deeply mine the high-dimensional features of node attributes, 94 and the obtained weight parameters were subsequently 95 transferred to the GAT.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Object-Oriented Semi-Supervised Land-Use/Land-Cover Change Detection Method Based on Siamese Autoencoder Graph Attention Network

Wu,

Xie,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Change detection via remote sensing data is a 8 popular method for monitoring land cover/land use. Graph 9 attention network (GAT) is a method that can improve the change detection performance of land cover/land use monitoring by enhancing the feature representation of remote sensing images. However, the shortcomings of connection sparsity and insufficient sample feature mining of the GAT affect the application of these methods in change detection. This paper proposes a Siamese autoencoder graph attention networks for object-oriented land cover/land use change detection via high-resolution remote sensing, which is useful for semi-supervised problem methods with poor simplicity. First, we reduce the pressure of graph network model operations and obtain multidimensional features via the growing multilevel segmentation strategy (GMSS). The adjacency matrix is established by adding strongly connected edges via the weighted difference similarity matching method (WDSM) with image objects as nodes. Second, we use the Siamese autoencoder to pretrain the node features and migrate the weight parameters to the GAT feature extraction layer. Finally, a small number of samples are selected to train the GAT and predict all nodes. The experimental results show that the average overall accuracy of the proposed method is 95.41%, and the average F1 score is 89.35%, which are at least 5.04% and 10.84% better than those of other typical methods, such as the graph convolutional network (GCN). In particular, detecting roads and bare soil is significantly better than that of other methods.

show abstract

Section: Semi-supervised Learningmentioning

confidence: 99%

mentioning

confidence: 99%

An Object-Oriented Semi-Supervised Land-Use/Land-Cover Change Detection Method Based on Siamese Autoencoder Graph Attention Network

Wu,

Xie,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Expanding on this, Chen et al have proposed CD methods that combine local and non-local graph structures [34,35], Zheng et al have proposed global and local graph-based DI enhancement methods [13] and a change smoothness method [36] for CD. Furthermore, numerous methods based on graph neural networks (GNN) have also been introduced for SAR CD tasks, such as the dynamic graph-level neural network [37], the multi-scale graph convolutional network [38], the variational graph auto-encoder network [39] and the graph-based knowledge supplement network [40].…”

Section: Related Workmentioning

confidence: 99%

A Multi-Scale Graph Based on Spatio-Temporal-Radiometric Interaction for SAR Image Change Detection

Zhang,

Jiang,

Kou

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) in remote sensing imagery has found broad applications in ecosystem service assessment, disaster evaluation, urban planning, land utilization, etc. In this paper, we propose a novel graph model-based method for synthetic aperture radar (SAR) image CD. To mitigate the influence of speckle noise on SAR image CD, we opt for comparing the structures of multi-temporal images instead of the conventional approach of directly comparing pixel values, which is more robust to the speckle noise. Specifically, we first segment the multi-temporal images into square patches at multiple scales and construct multi-scale K-nearest neighbor (KNN) graphs for each image, and then develop an effective graph fusion strategy, facilitating the exploitation of multi-scale information within SAR images, which offers an enhanced representation of the complex relationships among features in the images. Second, we accomplish the interaction of spatio-temporal-radiometric information between graph models through graph mapping, which can efficiently uncover the connections between multi-temporal images, leading to a more precise extraction of changes between the images. Finally, we use the Markov random field (MRF) based segmentation method to obtain the binary change map. Through extensive experimentation on real datasets, we demonstrate the remarkable superiority of our methodologies by comparing with some current state-of-the-art methods.

show abstract

“…The field of homogeneous change detection has seen significant advancements with the application of deep-learning techniques. These innovations have led to more sophisticated and efficient methods for analyzing changes in both optical remote sensing images and hyperspectral images, as well as SAR images [11][12][13][14][15][16][17][18][19][20][21][22][23]. For instance, Wu et al [14] proposed a spatial-temporal association-enhanced mobile-friendly vision transformer specifically designed for the change detection of high-resolution images.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al [18] presented a novel approach combining a convolution and attention mixer specifically for SAR image change detection, showcasing the ongoing evolution of methodologies. Su et al [19] developed an unsupervised method utilizing a variational graph auto-encoder network for object-based small area change detection in SAR images, which offers benefits in reducing the adverse effects of class imbalance and suppressing speckle noise. Zhang et al [20] introduced a robust unsupervised method for small area change detection from SAR imagery, employing a convolutional wavelet neural network, further emphasizing the field's progression towards addressing specific challenges in SAR image analysis.…”

Section: Introductionmentioning

confidence: 99%

Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and Two-Level Clustering

Li,

Ma,

Zhang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) change detection provides a powerful tool for continuous, reliable, and objective observation of the Earth, supporting a wide range of applications that require regular monitoring and assessment of changes in the natural and built environment. In this paper, we introduce a novel SAR image change detection method based on principal component analysis and two-level clustering. First, two difference images of the log-ratio and mean-ratio operators are computed, then the principal component analysis fusion model is used to fuse the two difference images, and a new difference image is generated. To incorporate contextual information during the feature extraction phase, Gabor wavelets are used to obtain the representation of the difference image across multiple scales and orientations. The maximum magnitude across all orientations at each scale is then concatenated to form the Gabor feature vector. Following this, a cascading clustering algorithm is developed within this discriminative feature space by merging the first-level fuzzy c-means clustering with the second-level neighbor rule. Ultimately, the two-level combination of the changed and unchanged results produces the final change map. Five SAR datasets are used for the experiment, and the results show that our algorithm has significant advantages in SAR change detection.

show abstract

Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery

Cited by 9 publications

References 47 publications

An Object-Oriented Semi-Supervised Land-Use/Land-Cover Change Detection Method Based on Siamese Autoencoder Graph Attention Network

An Object-Oriented Semi-Supervised Land-Use/Land-Cover Change Detection Method Based on Siamese Autoencoder Graph Attention Network

A Multi-Scale Graph Based on Spatio-Temporal-Radiometric Interaction for SAR Image Change Detection

Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and Two-Level Clustering

Contact Info

Product

Resources

About