CNN-Based InSAR Denoising and Coherence Metric

Mukherjee, Subhayan; Zimmer, Aaron; Kottayil, Navaneeth Kamballur; Sun, Xinyao; Ghuman, Parwant; Cheng, Irene

doi:10.1109/icsens.2018.8589920

Cited by 13 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active radar imaging is an important tool for detection and recognition of targets as well for the analysis of natural and man-made scenes. Radar images in a broader sense include unidimensional high-resolution range profiles (HRRP) [509], [510], [512], [523], two-dimensional SAR and ISAR images [273]- [275], [279], micro-doppler images [551]- [555] and range-doppler images [556]- [558]. Several ML-based techniques have been developed for radar image processing, particularly for what concerns Synthetic Aperture Radar (SAR) and Inverse Synthetic Aperture Radar (ISAR).…”

Section: Radar Images Processingmentioning

confidence: 99%

“…To solve the notorious problem of gradients vanishing and accelerate training convergence, a AE model was employed in [295] to denoise multisource SAR images, which adopted residual learning strategy by skip-connection operation. AE-CNN architecture was developed in [279] for InSAR images denoising in the absence of clean ground truth images. This method can reduce artefact in estimated coherence through intelligent preprocessing of training data.…”

Section: A Sar Images Processingmentioning

confidence: 99%

“…As a demonstration of the interest in this field, in the recent years, the Defense Advanced Research Projects Agency (DARPA) has launched many projects in this field, such as the radio frequency machine learning system (RFMLS) project [9]- [12], the behavior learning for adaptive electronic warfare (BLADE) project [13], [14], and the adaptive radar countermeasures (ARC) project [15]. In addition to DARPA's projects, there is ample support from the scientific literature, such as radar emitter recognition and classification [110], [147], [150], [152], radar image processing (e.g., synthetic aperture radar (SAR) image denoising [273]- [276], [279], data augmentation [251]- [255], automatic target recognition (ATR) [304], [310]- [316], [326], target detection [585], [587], also with specific emphasis on ship detection [472]- [474], [476], [477], anti-jamming [576], optimal waveform design [580], array antenna selection [586], and cognitive electronic warfare (CEW) [584]. These ML algorithms include traditional machine learning (e.g., support vector machines (SVMs), decision tree (DT), random forest (RF), boosting methods), and deep learning (e.g., deep belief networks (DBNs), autoencoders (AEs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs)).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing

Lang,

Fu,

Martorella

et al. 2020

Preprint

View full text Add to dashboard Cite

Modern radar systems have high requirements in terms of accuracy, robustness and real-time capability when operating on increasingly complex electromagnetic environments. Traditional radar signal processing (RSP) methods have shown some limitations when meeting such requirements, particularly in matters of target classification. With the rapid development of machine learning (ML), especially deep learning, radar researchers have started integrating these new methods when solving RSP-related problems. This paper aims at helping researchers and practitioners to better understand the application of ML techniques to RSP-related problems by providing a comprehensive, structured and reasoned literature overview of ML-based RSP techniques. This work is amply introduced by providing general elements of ML-based RSP and by stating the motivations behind them. The main applications of ML-based RSP are then analysed and structured based on the application field. This paper then concludes with a series of open questions and proposed research directions, in order to indicate current gaps and potential future solutions and trends.

show abstract

Section: Radar Images Processingmentioning

confidence: 99%

Section: A Sar Images Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing

Lang,

Fu,

Martorella

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…CNNs' use in InSAR phase processing in particular has been limited to volcano deformation monitoring [22] via transfer learning using a popular pre-trained optical image classification CNN [23], but not direct training on InSAR data. Recent CNN-based InSAR phase filtering and coherence estimation/classification [24], [25] performed training directly on InSAR data, but their filtering and coherence estimation is separated, and their "raw" coherence is generated/preprocessed using traditional methods. In contrast, GenInSAR performs joint phase filtering and coherence estimation using only a single neural network.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation

Mukherjee

Zimmer

Sun

et al. 2021

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

Earth's physical properties like atmosphere, topography and ground instability can be determined by differencing billions of phase measurements (pixels) in subsequent matching Interferometric Synthetic Aperture Radar (InSAR) images. Quality (coherence) of each pixel can vary from perfect information (1) to complete noise (0), which needs to be quantified, alongside filtering information-bearing pixels. Phase filtering is thus critical to InSAR's Digital Elevation Model (DEM) production pipeline, as it removes spatial inconsistencies (residues), immensely improving the subsequent unwrapping. Recent explosion in quantity of available InSAR data can facilitate Wide Area Monitoring (WAM) over several geographical regions, if effective and efficient automated processing can obviate manual quality-control. Advances in parallel computing architectures and Convolutional Neural Networks (CNNs) which thrive on them to rival human performance on visual pattern recognition makes this approach ideal for InSAR phase filtering for WAM, but remains largely unexplored. We propose "GenInSAR", a CNN-based generative model for joint phase filtering and coherence estimation. We use satellite and simulated InSAR images to show overall superior performance of GenInSAR over five algorithms qualitatively, and quantitatively using Phase and Coherence Root-Mean-Squared-Error, Residue Reduction Percentage, and Phase Cosine Error.

show abstract

“…In recent years, deep learning has been successfully applied to many fields, such as machine vision, optical image processing [27][28][29][30], and SAR image denoising [31][32][33]. In addition, the research of deep learning in the field of interferometric SAR has also begun to sprout [34][35][36]. In this paper, we propose a deep learning-based method to filter the interferometric phase for InSAR, which can better balance the noise suppression capacity and phase detail preservation capacity in order to obtain higher-precision results and ensure computational efficiency.…”

Section: Introductionmentioning

confidence: 99%

A Phase Filtering Method with Scale Recurrent Networks for InSAR

Zhang

Zhou

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Phase filtering is a key issue in interferometric synthetic aperture radar (InSAR) applications, such as deformation monitoring and topographic mapping. The accuracy of the deformation and terrain height is highly dependent on the quality of phase filtering. Researchers are committed to continuously improving the accuracy and efficiency of phase filtering. Inspired by the successful application of neural networks in SAR image denoising, in this paper we propose a phase filtering method that is based on deep learning to efficiently filter out the noise in the interferometric phase. In this method, the real and imaginary parts of the interferometric phase are filtered while using a scale recurrent network, which includes three single scale subnetworks based on the encoder-decoder architecture. The network can utilize the global structural phase information contained in the different-scaled feature maps, because RNN units are used to connect the three different-scaled subnetworks and transmit current state information among different subnetworks. The encoder part is used for extracting the phase features, and the decoder part restores detailed information from the encoded feature maps and makes the size of the output image the same as that of the input image. Experiments on simulated and real InSAR data prove that the proposed method is superior to three widely-used phase filtering methods by qualitative and quantitative comparisons. In addition, on the same simulated data set, the overall performance of the proposed method is better than another deep learning-based method (DeepInSAR). The runtime of the proposed method is only about 0.043s for an image with a size of 1024×1024 pixels, which has the significant advantage of computational efficiency in practical applications that require real-time processing.

show abstract

CNN-Based InSAR Denoising and Coherence Metric

Cited by 13 publications

References 32 publications

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing

A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing

An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation

A Phase Filtering Method with Scale Recurrent Networks for InSAR

Contact Info

Product

Resources

About