PolSAR image deep learning super-resolution model based on multi-scale attention mechanism

LIN Liupeng; LI Jie; SHEN Huanfeng

doi:10.11834/jrs.20233002

Views : 0 下载量: 104 CSCD: 0 更多指标

R-PDF
PDF
Export
Share
Collection
Album

PolSAR image deep learning super-resolution model based on multi-scale attention mechanism
Pages: 1-10(2023)
Published Online： 15 May 2023 ，
DOI： 10.11834/jrs.20233002

扫描看全文

林镠鹏，李杰，沈焕锋.XXXX.基于多尺度注意力机制的PolSAR深度学习超分辨率模型.遥感学报，XX（XX）： 1-10

LIN Liupeng，LI Jie，SHEN Huanfeng. XXXX. PolSAR image deep learning super-resolution model based on multi-scale attention mechanism. National Remote Sensing Bulletin， XX（XX）：1-10
林镠鹏，李杰，沈焕锋.XXXX.基于多尺度注意力机制的PolSAR深度学习超分辨率模型.遥感学报，XX（XX）： 1-10 DOI： 10.11834/jrs.20233002.

LIN Liupeng，LI Jie，SHEN Huanfeng. XXXX. PolSAR image deep learning super-resolution model based on multi-scale attention mechanism. National Remote Sensing Bulletin， XX（XX）：1-10 DOI： 10.11834/jrs.20233002.

摘要

全极化合成孔径雷达影像（PolSAR）可提供丰富的极化信息，但成像系统限制使其空间分辨率受到制约。为此，本文基于深度学习框架，提出一种基于多尺度注意力机制的超分辨率重建网络（MS-PSRN），通过对低分辨率PolSAR影像进行分辨率增强，生成高分辨率的PolSAR影像。在该模型框架下，采用多尺度注意力模块对不同尺度下的地物目标进行特征提取；提出联合式与分离式两种内嵌方式，在模型中嵌入通道注意力与空间注意力，利用注意力机制的权值重校准特性，增强PolSAR影像的极化信息与空间信息；引入残差信息蒸馏机制，提取判别性特征并对模型参数进行压缩；提出自适应损失函数对网络训练过程进行约束以提升模型的数值拟合能力以及边缘信息保持能力。本文采用RADARSAT-2卫星的模拟数据与真实数据两个数据集对提出的方法进行验证。空间信息实验结果表明，本文方法在目视结果与定量指标中均优于对比算法，具有更高的空间纹理细节重建精度与较低的重建误差。极化信息保持测试表明，本文方法可在提升空间分辨率的同时，有效保持PolSAR影像的极化信息。

Abstract

Fully polarimetric synthetic aperture radar imagery (PolSAR) can provide rich polarimetric information

however

due to the limitations of the system's signal bandwidth and the physical size of the antenna

the spatial resolution of the SAR imaging system is restricted while acquiring multiple polarization information. To solve this problem

based on the deep learning framework

this paper proposes a multi-scale attention-based PolSAR super-resolution network (MS-PSRN)

which performs super-resolution reconstruction on the low-resolution full-polarimetric SAR images to generate the fully polarimetric SAR images with high spatial resolution. Under this super-resolution reconstruction framework

this paper uses a multi-scale architecture to fully extract the feature information of objects at different scales. On this basis

the spatial attention mechanism and the channel attention mechanism are introduced to recalibrate the feature maps

which is used to enhance the reconstruction performance of spatial details and improve the ability to maintain polarization information respectively. Two attention mechanism embedding methods

joint and separated

are proposed to cope with the spatial size and quantity changes of the feature maps processed by the encoder and decoder. This paper introduces a residual information distillation mechanism

extracts discriminative features through feature distillation

and compresses model parameters at the same time. In addition

the adaptive loss function is proposed to constrain the network training process and improve the model's numerical fitting ability and edge information preservation ability. In this paper

the proposed method is verified by two data sets

which are the simulated data and the real data produced by RADARSAT-2 images. The experimental results of spatial information show that the proposed method is superior to the comparison algorithms in both visual results and quantitative indicators

and has higher texture detail reconstruction accuracy and lower reconstruction error. The polarimetric information preservation test shows that the proposed method can effectively preserve the polarimetric information of PolSAR images while improving spatial resolution.

关键词

全极化合成孔径雷达超分辨率重建深度学习遥感多尺度注意力机制

Keywords

fully polarimetric synthetic aperture radarsuper resolutiondeep learningremote sensingmulti-scaleattention mechanism

references

Chen J. and Yang J., 2007. Super-resolution of polarimetric SAR images for ship detection, 2007 International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications. IEEE, pp. 1499-1502.

Fan C., Gong J., Zhu J., Liao M., 2009. Super-resolution reconstruction of ALOS-PRISM remote sensing images[J]. Journal of Remote Sensing, 13(1):75-82.

范冲, 龚健雅, 朱建军, 廖明生, 2009. ALOS-PRISM遥感影像超分辨率重建. 遥感学报, 13(01): 75-82.

Fu J., Liu J., Tian H., Li Y., Bao Y., Fang Z. and Lu, H., 2019. Dual attention network for scene segmentation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146-3154.

He K., Zhang X., Ren S. and Sun, J., 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, Proceedings of the IEEE international conference on computer vision, pp. 1026-1034.

He Z and He D. 2020. Deep learning-based super-resolution for GF-4 satellite imagery. Journal of Remote Sensing， 24（12）：1500-1510.

贺智, 贺丹, 2020. 基于深度学习的高分四号卫星图像超分辨率重建. 遥感学报, 24(12): 1500-1510.

Kingma D.P. and Ba J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Lin L., Li J., Yuan Q. and Shen, H., 2019. Polarimetric SAR Image Super-Resolution VIA Deep Convolutional Neural Network, IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp. 3205-3208.

Liu J., Tang, J. Wu, G., 2020. Residual feature distillation network for lightweight image super-resolution, European Conference on Computer Vision. Springer, pp. 41-55.

Pastina D., Lombardo P., Farina A. and Daddi P., 2001. Super-resolution of polarimetric SAR images of a ship, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No. 01CH37217). IEEE, pp. 2343-2345.

Qi Z., Yeh, A.G.-O., Li, X. Lin, Z., 2012. A novel algorithm for land use and land cover classification using RADARSAT-2 polarimetric SAR data. Remote Sensing of Environment, 118: 21-39.

Shen H., Lin L., Li J., Yuan Q. and Zhao, L., 2020. A residual convolutional neural network for polarimetric SAR image super-resolution. ISPRS Journal of Photogrammetry and Remote Sensing, 161: 90-108.

Shi L., Sun W., Yang J., Li P. and Lu, L., 2015. Building collapse assessment by the use of postearthquake Chinese VHR airborne SAR. IEEE Geoscience and Remote Sensing Letters, 12(10): 2021-2025.

Suwa K. and Iwamoto M., 2006. A two-dimensional bandwidth extrapolation technique for polarimetric synthetic aperture radar images. IEEE Transactions on Geoscience and Remote Sensing, 45(1): 45-54.

Wang F., Jiang M., Qian C., Yang S., Li C., Zhang H., Wang X. and Tang, X., 2017. Residual attention network for image classification, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3156-3164.

Wang Y. and Liu H., 2015. PolSAR ship detection based on superpixel-level scattering mechanism distribution features. IEEE Geoscience and Remote Sensing Letters, 12(8): 1780-1784.

Yamaguchi Y., Moriyama T., Ishido M. and Yamada H., 2005. Four-component scattering model for polarimetric SAR image decomposition. IEEE Transactions on geoscience and remote sensing, 43(8): 1699-1706.

Zamir S.W., Arora A., Khan S., Hayat M., Khan F.S., Yang M.-H. and Shao, L., 2021. Multi-stage progressive image restoration, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14821-14831.

Zeiler M.D., Krishnan D., Taylor G.W. and Fergus R., 2010. Deconvolutional networks, 2010 IEEE Computer Society Conference on computer vision and pattern recognition. IEEE, pp. 2528-2535.

Zhang L., Zou B., Hao H. and Zhang, Y., 2011. A novel super-resolution method of PolSAR images based on target decomposition and polarimetric spatial correlation. International journal of remote sensing, 32(17): 4893-4913.

Zhang T., Jiang L., Xiang D., Ban Y., Pei L. and Xiong, H., 2019. Ship detection from PolSAR imagery using the ambiguity removal polarimetric notch filter. ISPRS Journal of Photogrammetry and Remote Sensing, 157: 41-58.

Zhang Y., Li K., Li K., Wang L., Zhong B. and Fu, Y., 2018a. Image super-resolution using very deep residual channel attention networks, Proceedings of the European conference on computer vision (ECCV), pp. 286-301.

Zhang Y., Tian Y., Kong Y., Zhong B. and Fu Y., 2018b. Residual dense network for image super-resolution, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2472-2481.

Zhao L., Yang J., Li P., Zhang L., Shi L. and Lang, F., 2013. Damage assessment in urban areas using post-earthquake airborne PolSAR imagery. International journal of remote sensing, 34(24): 8952-8966.

Zou B., Hao, H. Guo, X., 2008. Super-resolution of polarimetric sar images based on target decomposition and polarimetric spatial correlation, IGARSS 2008-2008 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp. II-911-II-914.

Alert me when the article has been cited

提交

Weakly supervised scale adaptation data augmentation for scene classification of high-resolution remote sensing images

Recognition of small-target ships in complex satellite images

Hybrid Spatial Pyramid Pooling Network to Change Detection for High Resolution Remote Sensing Images

Optical-signal token guided change detection network for heterogeneous remote sensing image

Research progress on hyperspectral anomaly detection