Adaptive pseudo-p-norm regularization based De-speckling of SAR images

Yan, Meng; Zhou, Zeming; Liu, Yudi; Luo, Qixiang

doi:10.1080/2150704x.2018.1519268

Cited by 5 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wagner et al [32] proposed a deep learning SAR ATR system using regularization and prioritized classes to improve the convergence properties. Meng et al [33] adopted an adaptive pseudo-p-norm regularization based despeckling SAR images method to provide a high-quality interpretation of SAR data. Ni et al [34] presented the L 1 /L 2regularization SAR imaging via complex image data to better reconstructing the image target detection task.…”

Section: 2mentioning

confidence: 99%

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization

Zhai

Deng

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Though Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) via Convolutional Neural Networks (CNNs) has made huge progress toward deep learning, some key issues still remain unsolved due to the lack of sufficient samples and robust model. In this paper, we proposed an efficient transferred Max-Slice CNN (MS-CNN) with L2-Regularization for SAR ATR, which could enrich the features and recognize the targets with superior performance. Firstly, the data amplification method is presented to reduce the computational time and enrich the raw features of SAR targets. Secondly, the proposed MS-CNN framework with L2-Regularization is trained to extract robust features, in which the L2-Regularization is incorporated to avoid the overfitting phenomenon and further optimizing our proposed model. Thirdly, transfer learning is introduced to enhance the feature representation and discrimination, which could boost the performance and robustness of the proposed model on small samples. Finally, various activation functions and dropout strategies are evaluated for further improving recognition performance. Extensive experiments demonstrated that our proposed method could not only outperform other state-of-the-art methods on the public and extended MSTAR dataset but also obtain good performance on the random small datasets.

show abstract

Section: 2mentioning

confidence: 99%

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization

Zhai

Deng

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Speckle reduces the visual quality of SAR images and can hamper their interpretation, affecting the accuracy of their classification and analysis (Gui, Xue, and Li, 2018;Torres et al 2014). Therefore, one important step in the processing and, subsequently, analysis of SAR images consists of reducing the speckle effect before the extraction of the desired information (Lang, Yang and Li, 2015;Meng et al 2018;Yue, Xu and Jin 2018). The filtering methods are prepared according to algorithms that are based on the speckle statistics and can be grouped in the frequency (wavelet) and spatial domains (Shafiei, Beheshti and Yazdian 2018;Yue, Xu and Jin 2018;Sivaranjani, Roomi and Senthilarasi 2019).…”

Section: Introductionmentioning

confidence: 99%

Speckle reduction for Sentinel-1A SAR images in the Semi-arid caatinga region, Brazil

Jesus,

Kuplich,

Barreto

et al. 2023

Bol. Ciênc. Geod.

View full text Add to dashboard Cite

Due to the absence of studies related to the digital processing of synthetic aperture radar (SAR) images in the semi-arid region of Brazil, the aim of this study was to test different filters for reducing speckle noise in SAR images, serving as a reference for choosing the most suitable filter for different studies in this vegetation. The filters: Gamma Map, Lee Sigma, Median, Frost and Refined Lee in different window sizes were tested on the VV, VH and VH/VV polarizations in the Sentinel-1A images, verifying the responses under the influence of the dry and post-rainy period in the Caatinga vegetation. In the state of Sergipe, Brazil, 30 samples of Caatinga fragments obtained from Sentinel-1A images for the dry and post-rainy season were selected. For all images evaluated, the values of the averages of the equivalent number of looks (ENL) were compared by the Tukey test at 5% significance. The Gamma filter showed the highest amount of means ( 22) with the highest ENL values, followed by Median (5). The generation of ENL results and their comparison, considering all variables used, was essential to serve as a basis for choosing the filtering method in studies that use data from Sentinel-1A in the Caatinga region.

show abstract

“…There are few studies have successfully employed the adaptive norms in the field of image denoising, and achieved desirable results [33,34]. It could be an ideal solution to address the problems of the trade-off in the HP and 1 trend filtering methods, which equips the capacity to balance the noise removal and signal preserving.…”

Section: Introductionmentioning

confidence: 99%

Piecewise Adaptive-Norm Trend Filtering Method for ICESat/GLAS Waveform Data Denoising

et al. 2020

View full text Add to dashboard Cite

The Geoscience Laser Altimeter System (GLAS) aboard Ice, Cloud and land Elevation Satellite (ICESat) was able to capture the full waveform of backscattered laser pulse. However, the accuracy of the surface information extracted from the waveform was vulnerable to background noise. In this paper, a piecewise adaptive lq-norm trend filtering method is proposed for the GLAS full waveform denoising on the basis of trend filtering. To minimize the loss of useful signal while removing the noise, the proposed method adaptively assigns different norms to the smooth constraints according to the local signal energy. The filtered results can then be obtained by iteratively minimizing the hybrid-norm loss function. The proposed method is tested on both the simulated waveforms and real GLAS waveform data. In the simulated experiments, the quantitative evaluation is conducted with the filtered waveforms, as well as the results after waveform decomposition. For comparison, the most commonly used waveform filtering methods, i.e. Gaussian filtering, wavelet transform, Empirical model decomposition and 1 trend filtering, are involved in the experiments. The results show that the proposed method outperforms the mainstream methods on waveform filtering, in terms of removing noise and preserving the shape and energy amplitude of the GLAS waveforms.

show abstract

Adaptive pseudo-p-norm regularization based De-speckling of SAR images

Cited by 5 publications

References 20 publications

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization

Speckle reduction for Sentinel-1A SAR images in the Semi-arid caatinga region, Brazil

Piecewise Adaptive-Norm Trend Filtering Method for ICESat/GLAS Waveform Data Denoising

Contact Info

Product

Resources

About

Adaptive pseudo-p-norm regularization based De-speckling of SAR images

Cited by 5 publications

References 20 publications

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization

Speckle reduction for Sentinel-1A SAR images in the Semi-arid caatinga region, Brazil

Piecewise Adaptive-Norm Trend Filtering Method for ICESat/GLAS Waveform Data Denoising

Contact Info

Product

Resources

About

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization

Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L²-Regularization