scholarly journals Compressive Sensing-Based SAR Image Reconstruction from Sparse Radar Sensor Data Acquisition in Automotive FMCW Radar System

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7283
Author(s):  
Seongwook Lee ◽  
Yunho Jung ◽  
Myeongjin Lee ◽  
Wookyung Lee
Keyword(s):  
Fourier Transform ◽  
Image Reconstruction ◽  
Data Acquisition ◽  
Compressive Sensing ◽  
Sensor Data ◽  
Sar Image ◽  
Radar Sensor ◽  
Sar Images ◽  
Recovery Method

In this paper, we propose a method for reconstructing synthetic aperture radar (SAR) images by applying a compressive sensing (CS) technique to sparsely acquired radar sensor data. In general, SAR image reconstruction algorithms require radar sensor data acquired at regular spatial intervals. However, when the speed of the radar-equipped platform is not constant, it is difficult to consistently perform regular data acquisitions. Therefore, we used the CS-based signal recovery method to efficiently reconstruct SAR images even when regular data acquisition was not performed. In the proposed method, we used the l1-norm minimization to overcome the non-uniform data acquisition problem, which replaced the Fourier transform and inverse Fourier transform in the conventional SAR image reconstruction method. In addition, to reduce the phase distortion of the recovered signal, the proposed method was applied to each of the in-phase and quadrature components of the acquired radar sensor data. To evaluate the performance of the proposed method, we conducted experiments using an automotive frequency-modulated continuous wave radar sensor. Then, the quality of the SAR image reconstructed with data acquired at regular intervals was compared with the quality of images reconstructed with data acquired at non-uniform intervals. Using the proposed method, even if only 70% of the regularly acquired radar sensor data was used, a SAR image having a correlation of 0.83 could be reconstructed.

scholarly journals Drone SAR Image Compression Based on Block Adaptive Compressive Sensing

2021 ◽  
Vol 13 (19) ◽  
pp. 3947
Author(s):  
Jihoon Choi ◽  
Wookyung Lee
Keyword(s):  
Compressive Sensing ◽  
Side Information ◽  
Signal To Noise Ratio ◽  
Discrete Wavelet ◽  
Sar Image ◽  
Measurement Matrix ◽  
Sar Images ◽  
Recovery Method ◽  
Iterative Thresholding ◽  
Thresholding Algorithm

In this paper, an adaptive block compressive sensing (BCS) method is proposed for compression of synthetic aperture radar (SAR) images. The proposed method enhances the compression efficiency by dividing the magnitude of the entire SAR image into multiple blocks and subsampling individual blocks with different compression ratios depending on the sparsity of coefficients in the discrete wavelet transform domain. Especially, a new algorithm is devised that selects the best block measurement matrix from a predetermined codebook to reduce the side information about measurement matrices transferred from the remote sensing node to the ground station. Through some modification of the iterative thresholding algorithm, a new clustered BCS recovery method is proposed that classifies the blocks into multiple clusters according to the compression ratio and iteratively reconstructs the SAR image from the received compressed data. Since the blocks in the same cluster are concurrently reconstructed using the same measurement matrix, the proposed structure mitigates the increase in computational complexity when adopting multiple measurement matrices. Using existing SAR images and experimental data obtained by self-made drone SAR and vehicular SAR systems, it is shown that the proposed scheme provides a good tradeoff between the peak signal-to-noise ratio and the computational load compared to conventional BCS-based compression techniques.

scholarly journals Dialectical GAN for SAR Image Translation: From Sentinel-1 to TerraSAR-X

2018 ◽  
Vol 10 (10) ◽  
pp. 1597 ◽  
Author(s):  
Dongyang Ao ◽  
Corneliu Octavian Dumitru ◽  
Gottfried Schwarz ◽  
Mihai Datcu
Keyword(s):  
Sar Image ◽  
Sar Images ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Image Translation ◽  
Gram Matrices ◽  
Processing Resources ◽  
Ground Coverage

With more and more SAR applications, the demand for enhanced high-quality SAR images has increased considerably. However, high-quality SAR images entail high costs, due to the limitations of current SAR devices and their image processing resources. To improve the quality of SAR images and to reduce the costs of their generation, we propose a Dialectical Generative Adversarial Network (Dialectical GAN) to generate high-quality SAR images. This method is based on the analysis of hierarchical SAR information and the “dialectical” structure of GAN frameworks. As a demonstration, a typical example will be shown, where a low-resolution SAR image (e.g., a Sentinel-1 image) with large ground coverage is translated into a high-resolution SAR image (e.g., a TerraSAR-X image). A new algorithm is proposed based on a network framework by combining conditional WGAN-GP (Wasserstein Generative Adversarial Network—Gradient Penalty) loss functions and Spatial Gram matrices under the rule of dialectics. Experimental results show that the SAR image translation works very well when we compare the results of our proposed method with the selected traditional methods.

Sampling from the 𝒢 I 0 distribution

2018 ◽  
Vol 24 (4) ◽  
pp. 271-287 ◽  
Author(s):  
Debora Chan ◽  
Andrea Rey ◽  
Juliana Gambini ◽  
Alejandro C. Frery
Keyword(s):  
Programming Languages ◽  
Processing Time ◽  
Signal To Noise Ratio ◽  
Simulated Data ◽  
Synthetic Aperture ◽  
Type Ii ◽  
Sar Image ◽  
Sar Images ◽  
Gamma Distributions

Abstract Synthetic Aperture Radar (SAR) images are widely used in several environmental applications because they provide information which cannot be obtained with other sensors. The {\mathcal{G}_{I}^{0}} distribution is an important model for these images because of its flexibility (it provides a suitable way for modeling areas with different degrees of texture, reflectivity and signal-to-noise ratio) and tractability (it is closely related to the Snedekor-F, Pareto Type II, and Gamma distributions). Simulated data are important for devising tools for SAR image processing, analysis and interpretation, among other applications. We compare four ways for sampling data that follow the {\mathcal{G}_{I}^{0}} distribution, using several criteria for assessing the quality of the generated data and the consumed processing time. The experiments are performed running codes in four different programming languages. The experimental results indicate that although there is no overall best method in all the considered programming languages, it is possible to make specific recommendations for each one.

scholarly journals Optimization Methods of Compressively Sensed Image Reconstruction Based on Single-Pixel Imaging

2020 ◽  
Vol 10 (9) ◽  
pp. 3288 ◽  
Author(s):  
Ziran Wei ◽  
Jianlin Zhang ◽  
Zhiyong Xu ◽  
Yong Liu
Keyword(s):  
Image Reconstruction ◽  
Compressive Sensing ◽  
Imaging System ◽  
Optimization Methods ◽  
Superior Performance ◽  
Gram Matrix ◽  
Constraint Matrix ◽  
Single Pixel ◽  
Sensing Matrices

According to the theory of compressive sensing, a single-pixel imaging system was built in our laboratory, and imaging scenes are successfully reconstructed by single-pixel imaging, but the quality of reconstructed images in traditional methods cannot meet the demands of further engineering applications. In order to improve the imaging accuracy of our single-pixel camera, some optimization methods of key technologies in compressive sensing are proposed in this paper. First, in terms of sparse signal decomposition, based on traditional discrete wavelet transform and the characteristics of coefficients distribution in wavelet domain, a constraint condition of the exponential decay is proposed and a corresponding constraint matrix is designed to optimize the original wavelet decomposition basis. Second, for the construction of deterministic binary sensing matrices in the single-pixel camera, on the basis of a Gram matrix, a new algorithm model and a new method of initializing a compressed sensing measurement matrix are proposed to optimize the traditional binary sensing matrices via mutual coherence minimization. The gradient projection-based algorithm is used to solve the new mathematical model and train deterministic binary sensing measurement matrices with better performance. Third, the proposed optimization methods are applied to our single-pixel imaging system for optimizing the existing imaging methods. Compared with the conventional methods of single-pixel imaging, the accuracy of image reconstruction and the quality of single-pixel imaging have been significantly improved by our methods. The superior performance of our proposed methods has been fully tested and the effectiveness has also been demonstrated by numerical simulation experiments and practical imaging experiments.

scholarly journals LIME-Based Data Selection Method for SAR Images Generation Using GAN

2022 ◽  
Vol 14 (1) ◽  
pp. 204
Author(s):  
Mingzhe Zhu ◽  
Bo Zang ◽  
Linlin Ding ◽  
Tao Lei ◽  
Zhenpeng Feng ◽  
...  
Keyword(s):  
Video Processing ◽  
Generative Adversarial Networks ◽  
Correct Prediction ◽  
Positive Contribution ◽  
Sar Image ◽  
Sar Images ◽  
Adversarial Networks ◽  
Image And Video Processing ◽  
Interpretable Model

Deep learning has obtained remarkable achievements in computer vision, especially image and video processing. However, in synthetic aperture radar (SAR) image recognition, the application of DNNs is usually restricted due to data insufficiency. To augment datasets, generative adversarial networks (GANs) are usually used to generate numerous photo-realistic SAR images. Although there are many pixel-level metrics to measure GAN’s performance from the quality of generated SAR images, there are few measurements to evaluate whether the generated SAR images include the most representative features of the target. In this case, the classifier probably categorizes a SAR image into the corresponding class based on “wrong” criterion, i.e., “Clever Hans”. In this paper, local interpretable model-agnostic explanation (LIME) is innovatively utilized to evaluate whether a generated SAR image possessed the most representative features of a specific kind of target. Firstly, LIME is used to visualize positive contributions of the input SAR image to the correct prediction of the classifier. Subsequently, these representative SAR images can be selected handily by evaluating how much the positive contribution region matches the target. Experimental results demonstrate that the proposed method can ally “Clever Hans” phenomenon greatly caused by the spurious relationship between generated SAR images and the corresponding classes.

Sar Image Denoising Based on Multifractal and Regularity Analysis

2012 ◽  
Vol 500 ◽  
pp. 534-539
Author(s):  
Yun Ping Chen ◽  
Yan Chen ◽  
Ling Tong
Keyword(s):  
Image Denoising ◽  
Electromagnetic Waves ◽  
Multifractal Spectrum ◽  
Speckle Noise ◽  
Structural Features ◽  
Sar Image ◽  
Hölder Exponent ◽  
Sar Images ◽  
Equivalent Number

Synthetic Aperture Radar (SAR) images are corrupted by multiplicative speckle noise, which is due to random interference of electromagnetic waves. The noise degrades the quality of images and makes them hard to be interpreted, analyzed and classified. It appears sensible to reduce speckle in SAR images, while the structural features and textural information are not lost. This paper applies the framework of multifractal and regularity analysis to SAR image enhancement and denoising. The method does not make explicit assumptions about the model of the noise, but rather supposes that image denoising is equivalent to increasing the Hölder exponent at each point. The image is characterized via its multifractal spectrum, which mode yields the most frequent Hölder exponent. This manipulation leads to a smooth image while preserving the useful information in the signal. In order to evaluate the restoration result, Equivalent Number of Look (ENL) and edge save index (ESI) are used as criterion. Better result is obtained when regularity increase equal 0.5 (δ=0.5).

Sign in / Sign up

Export Citation Format

Share Document