A Novel Attention Fully Convolutional Network Method for Synthetic Aperture Radar Image Segmentation

Yue, Zhenyu; Gao, Fei; Xiong, Qingxu; Wang, Jun; Hussain, Amir; Zhou, Huiyu

doi:10.1109/jstars.2020.3016064

Cited by 28 publications

(13 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model removes the nonlocal attention mechanism in AM-GAN, and other structures are the same as the AM-GAN. In addition, current mainstream, AM-FCN [ 43 ] embedded based on attention, Attention U-Net [ 44 ] fused on attention in both encoder and decoder, DANet [ 45 ] embedded based on dual attention, and SEVNet [ 46 ] fused on SE module are selected as comparison models. The four index values of accuracy, recall, precision, and F1-score are used for comparative evaluation.…”

Section: The Experiments and Results Analysismentioning

confidence: 99%

A Generative Adversarial Network Fused with Dual‐Attention Mechanism and Its Application in Multitarget Image Fine Segmentation

Yin

Zhou

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Aiming at the problem of insignificant target morphological features, inaccurate detection and unclear boundary of small-target regions, and multitarget boundary overlap in multitarget complex image segmentation, combining the image segmentation mechanism of generative adversarial network with the feature enhancement method of nonlocal attention, a generative adversarial network fused with attention mechanism (AM-GAN) is proposed. The generative network in the model is composed of residual network and nonlocal attention module, which use the feature extraction and multiscale fusion mechanism of residual network, as well as feature enhancement and global information fusion ability of nonlocal spatial-channel dual attention to enhance the target features in the detection area and improve the continuity and clarity of the segmentation boundary. The adversarial network is composed of fully convolutional networks, which penalizes the loss of information in small-target regions by judging the authenticity of prediction and label segmentation and improves the detection ability of the generative adversarial model for small targets and the accuracy of multitarget segmentation. AM-GAN can use the GAN’s inherent mechanism that reconstruct and repair high-resolution image, as well as the ability of nonlocal attention global receptive field to strengthen detail features, automatically learn to focus on target structures of different shapes and sizes, highlight salient features useful for specific tasks, reduce the loss of image detail features, improve the accuracy of small-target detection, and optimize the segmentation boundary of multitargets. Taking medical MRI abdominal image segmentation as a verification experiment, multitargets such as liver, left/right kidney, and spleen are selected for segmentation and abnormal tissue detection. In the case of small and unbalanced sample datasets, the class pixels’ accuracy reaches 87.37%, the intersection over union is 92.42%, and the average Dice coefficient is 93%. Compared with other methods in the experiment, the segmentation precision and accuracy are greatly improved. It shows that the proposed method has good applicability for solving typical multitarget image segmentation problems such as small-target feature detection, boundary overlap, and offset deformation.

show abstract

Section: The Experiments and Results Analysismentioning

confidence: 99%

A Generative Adversarial Network Fused with Dual‐Attention Mechanism and Its Application in Multitarget Image Fine Segmentation

Yin

Zhou

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…According to the experiment results in this letter, as long as the accuracy of the classification result exceeds certain threshold, good registration performance can be guaranteed. Through the investigation of existing remote sensing image classification algorithms, the accuracy of current feature classification already exceeded this required threshold [5–13]. This proves the feasibility of the regional‐feature‐based registration scheme.…”

Section: Discussionmentioning

confidence: 96%

“…Yue et al. [5] propose a classification method, which achieves a pixel accuracy (PA) of 95.79%, whereas Luo et al. [6] achieve an overall accuracy of 95.17%.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, recent research works on remote sensing image classification have made significant progress. Yue et al [5] propose a classification method, which achieves a pixel accuracy (PA) of 95.79%, whereas Luo et al [6] achieve an overall accuracy of 95.17%. Other recently proposed method typically reaches an accuracy of above 90% [7][8][9][10][11][12][13].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Analysis of feasibility and advantages of multi‐source image registration using regional features

Zeng

Zhu

et al. 2021

Electronics Letters

View full text Add to dashboard Cite

Automatic registration of multi-source remote sensing data is a challenging task due to the high non-linearity of radiometric differences among various data. Feature extraction is a key enabling technique in registration algorithm design. In this letter, we prove the feasibility of using extracted regional features for multi-source image registration. In particular, regional features can be extracted through pixel-level image classification, and existing off-the-shelf algorithms can be directly adopted. Experiment results demonstrate the robustness of the regionalfeature-based registration method.

show abstract

“…In [11], a 'encoderdecoder' CNN network with inception modules and skip connections is introduced for the semantic segmentation of wetland PolSAR images. In [12], a multi-scale attention based FCN (MANet) is presented combining multi-scale feature extraction and the attention mechanism. In [13], a small yet efficient network (HR-SARNet) is proposed for the semantic segmentation of high-resolution SAR images.…”

Section: Introductionmentioning

confidence: 99%

MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images

Ding,

Zheng,

Lin

et al. 2020

Preprint

View full text Add to dashboard Cite

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the complexity of managing speckle noise. The Gaofen contest has provided open access a high-quality PolSAR semantic segmentation dataset. Taking this opportunity, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to effectively exploit the features learned from its different branches. Ablation studies show that the MP-ResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, with only a limited increase of computational costs. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

show abstract

A Novel Attention Fully Convolutional Network Method for Synthetic Aperture Radar Image Segmentation

Cited by 28 publications

References 46 publications

A Generative Adversarial Network Fused with Dual‐Attention Mechanism and Its Application in Multitarget Image Fine Segmentation

A Generative Adversarial Network Fused with Dual‐Attention Mechanism and Its Application in Multitarget Image Fine Segmentation

Analysis of feasibility and advantages of multi‐source image registration using regional features

MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images

Contact Info

Product

Resources

About