A residual convolutional neural network for polarimetric SAR image super-resolution

Shen, Huanfeng; Lin, Liupeng; Li, Jie; Yuan, Qiangqiang; Zhao, Lingli

doi:10.1016/j.isprsjprs.2020.01.006

Cited by 49 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LE is used for non-linear dimensionality reduction of polarimetric features and providing a compact low dimensional polarimetric feature space. While some studies have tried to analyse the polarimetric information [5][6][7], other ones have studied the valuable spatial features in PolSAR images. Generally, various methods have been used for contextual feature extraction in the remote sensing field.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Kernel‐based covariance descriptor for classification of polarimetric synthetic aperture radar images

Imani

2021

IET Radar Sonar & Navi

View full text Add to dashboard Cite

There are two types of important information in a polarimetric synthetic aperture radar (PolSAR) image: spatial features in two dimensions and polarimetric characteristics in the scattering dimension. Considering both polarimetric and spatial information is important for PolSAR image classification. Convolutional kernels show superior performance for extraction of spatial information from two dimensions of an image in convolutional neural networks (CNNs). But learning CNNs needs large enough training sets to achieve the optimum weights of kernels while there are not usually sufficient training samples for PolSAR images. To deal with this difficulty, a convolutional kernel‐based covariance descriptor (CKCD) is introduced for PolSAR image classification in this study. To extract contextual characteristics, compatible with the original image, the fixed‐valued convolutional kernels randomly selected from the image are used, which do not require any learning, and so do not need any training samples. To include more local spatial information and find the relation among the polarimetric features, the covariance descriptor is constructed on the extracted feature maps. Then, the polarimetric‐contextual features are given to a support vector machine with a matrix logarithm‐based kernel. Finally, the guided filter is applied to the initial classification map to result a smoothed classification map with preserved edges. The experiments on three real PolSAR images show superiority of the proposed CKCD method compared to several PolSAR classification methods such as 2DCNN and 3DCNN in small sample size situations.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Second, farther pixels with similar polarimetric characteristics and likely belonging to the same class of the central pixel have chance to be selected as K nearest neighbours and contribute in covariance matrix calculation. (5)…”

Section: Introductionmentioning

confidence: 99%

Convolutional Kernel‐based covariance descriptor for classification of polarimetric synthetic aperture radar images

Imani

2021

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…Lanaras et al [ 8 ] employed a CNN architecture to upsample the LR images in an end-to-end manner to super-resolve the multi-spectral imagery delivered by the Sentinel-2 satellite mission from about 60 Ground Sampling Distance (GSD) to 10 GSD. Shen et al [ 9 ] proposed a residual convolutional neural network in order to generate HR PolSAR images from LR ones, which focused on the change of pixel-wise difference instead of the slight but complex transformation between corresponding pixels. Salvetti et al [ 10 ] proposed a fully convolutional residual attention multi-image super-resolution (RAMS) to exploit spatial and temporal correlations to leverage multiple remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

A New Super Resolution Framework Based on Multi-Task Learning for Remote Sensing Images

Chang

2021

Sensors

View full text Add to dashboard Cite

Super-resolution (SR) algorithms based on deep learning have dominated in various tasks, including medical imaging, street view surveillance and face recognition. In the remote sensing field, most of the current SR methods utilize the low-resolution (LR) images that directly bicubic downsampled the high-resolution (HR) images as not only train set but also test set, thus achieving high PSNR/SSIM scores but showing performance drop in application because the degradation model in remote sensing images is subjected to Gaussian blur with unknown parameters. Inspired by multi-task learning strategy, we propose a multiple-blur-kernel super-resolution framework (MSF), in which a multiple-blur-kernel learning module (MLM) optimizes the parameters of the network transferable and sensitive for SR procedures with different blur kernels. Besides, to simultaneously exploit the prior of the large-scale remote sensing images and recurrent information in a single test image, a class-feature capture module (CCM) and an unsupervised learning module (ULM) are leveraged in our framework. Extensive experiments show that our framework outperforms the current state-of-the-art SR algorithms in remotely sensed imagery SR with unknown Gaussian blur kernel.

show abstract

“…The many advantages of SAR includes, among others, multi-polarization and variable angles, which allows SAR images to be widely used in geological surveys, military exercises, etc. [ 1 , 2 ]; however, due to its special coherent imaging mechanism, noise is inevitably generated in image acquisition, especially for speckle noise, resulting in serious inconvenience to the subsequent interpretation of the image processing; therefore, the effective suppression or removal of noise is one of the essential tasks required for SAR image pre-processing [ 3 ]. SAR can penetrate the earth’s surface as well as natural vegetation coverings, clearly and exhaustively map topography and geomorphology, and obtain high-resolution images of the earth’s surface; however, the color information of SAR images is relatively simple, and cannot adequately reflect the scene’s spectral information.…”

Section: Introductionmentioning

confidence: 99%

A Noisy SAR Image Fusion Method Based on NLM and GAN

Fang

Wang

et al. 2021

Entropy

View full text Add to dashboard Cite

The unavoidable noise often present in synthetic aperture radar (SAR) images, such as speckle noise, negatively impacts the subsequent processing of SAR images. Further, it is not easy to find an appropriate application for SAR images, given that the human visual system is sensitive to color and SAR images are gray. As a result, a noisy SAR image fusion method based on nonlocal matching and generative adversarial networks is presented in this paper. A nonlocal matching method is applied to processing source images into similar block groups in the pre-processing step. Then, adversarial networks are employed to generate a final noise-free fused SAR image block, where the generator aims to generate a noise-free SAR image block with color information, and the discriminator tries to increase the spatial resolution of the generated image block. This step ensures that the fused image block contains high resolution and color information at the same time. Finally, a fused image can be obtained by aggregating all the image blocks. By extensive comparative experiments on the SEN1–2 datasets and source images, it can be found that the proposed method not only has better fusion results but is also robust to image noise, indicating the superiority of the proposed noisy SAR image fusion method over the state-of-the-art methods.

show abstract

A residual convolutional neural network for polarimetric SAR image super-resolution

Cited by 49 publications

References 32 publications

Convolutional Kernel‐based covariance descriptor for classification of polarimetric synthetic aperture radar images

Convolutional Kernel‐based covariance descriptor for classification of polarimetric synthetic aperture radar images

A New Super Resolution Framework Based on Multi-Task Learning for Remote Sensing Images

A Noisy SAR Image Fusion Method Based on NLM and GAN

Contact Info

Product

Resources

About