scholarly journals HDRANet: Hybrid Dilated Residual Attention Network for SAR Image Despeckling

2019 ◽  
Vol 11 (24) ◽  
pp. 2921 ◽  
Author(s):  
Jingyu Li ◽  
Ying Li ◽  
Yayuan Xiao ◽  
Yunpeng Bai
Keyword(s):  
Network Architecture ◽  
State Of The Art ◽  
Speckle Noise ◽  
Superior Performance ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Attention Network ◽  
Quantitative Metrics ◽  
Proposed Model ◽  
And Performance

In order to remove speckle noise from original synthetic aperture radar (SAR) images effectively and efficiently, this paper proposes a hybrid dilated residual attention network (HDRANet) with residual learning for SAR despeckling. Firstly, HDRANet employs the hybrid dilated convolution (HDC) in lightweight network architecture to enlarge the receptive field and aggregate global information. Then, a simple yet effective attention module, convolutional block attention module (CBAM), is integrated into the proposed model to constitute a residual HDC attention block through skip connection, which further enhances representation power and performance of the model. Extensive experimental results on the synthetic and real SAR images demonstrate the superior performance of HDRANet over the state-of-the-art methods in terms of quantitative metrics and visual quality.

scholarly journals A Modification of Rician Distribution for SAR Image Modelling

2020 ◽  
Author(s):  
Oktay Karakuş ◽  
Ercan E Kuruoglu ◽  
Alin Achim
Keyword(s):  
Statistical Models ◽  
State Of The Art ◽  
Sea Surface ◽  
Superior Performance ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Frequency Bands ◽  
Rician Distribution ◽  
Proposed Model ◽  
Image Modelling

This paper presents a novel statistical model i.e. the Laplace-Rician distribution, for the characterisation of synthetic aperture radar (SAR) images. Since accurate statistical models lead to better results in applications such as target tracking, classification, or despeckling, characterising SAR images of various scenes including urban, sea surface, or agricultural, is essential. The proposed Laplace-Rician model is investigated for SAR images of several frequency bands and various scenes in comparison to state-of-the-art statistical models that include K, Weibull, and Lognormal. The results demonstrate the superior performance and flexibility of the proposed model for all frequency bands and scenes.

scholarly journals SAR Target Configuration Recognition via Product Sparse Representation

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3535
Author(s):  
Ming Liu ◽  
Shichao Chen ◽  
Fugang Lu ◽  
Mengdao Xing
Keyword(s):  
Sparse Representation ◽  
State Of The Art ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Product Model ◽  
Sar Images ◽  
Stationary Target ◽  
Target Configuration ◽  
Sparse Vector

Sparse representation (SR) has been verified to be an effective tool for pattern recognition. Considering the multiplicative speckle noise in synthetic aperture radar (SAR) images, a product sparse representation (PSR) algorithm is proposed to achieve SAR target configuration recognition. To extract the essential characteristics of SAR images, the product model is utilized to describe SAR images. The advantages of sparse representation and the product model are combined to realize a more accurate sparse representation of the SAR image. Moreover, in order to weaken the influences of the speckle noise on recognition, the speckle noise of SAR images is modeled by the Gamma distribution, and the sparse vector of the SAR image is obtained from q statistical standpoint. Experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) database. The experimental results validate the effectiveness and robustness of the proposed algorithm, which can achieve higher recognition rates than some of the state-of-the-art algorithms under different circumstances.

scholarly journals A Bayesian Joint Decorrelation and Despeckling approach for speckle reduction of SAR Images

2015 ◽  
Vol 1 (1) ◽  
Author(s):  
Caifeng Wang ◽  
LinLin Xu ◽  
David Clausi ◽  
Alexander Wong
Keyword(s):  
State Of The Art ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Speckle Reduction ◽  
Sar Images ◽  
Novel Approach ◽  
Maximum A Posterior ◽  
Sar Data ◽  
Sar Imagery ◽  
Posterior Estimation

<p>In this paper, we present a novel approach for joint decorrelation<br />and despeckling of synthetic aperture radar (SAR) imagery. An iterative<br />maximum a posterior estimation is performed to obtain the<br />correlation and speckle-free SAR data, which incorporates a correlation<br />model which realistically explores the physical correlated<br />process of speckle noise on signal in SAR imaging. The correlation<br />model is determined automatically via Bayesian estimation in the<br />log-Fourier domain and patch-wise computation is used to account<br />for spatial nonstationarities existing in SAR data. The proposed<br />approach is compared to a state-of-the-art despeckling technique<br />using both simulated and real SAR data. Experimental results illustrate<br />its improvement in preserving the structural detail, especially<br />the sharpness of the edges, when suppressing speckle noise.</p>

Segmentation of SAR Image using Fuzzy C-Means and Filters

2020 ◽  
Vol 8 (1) ◽  
pp. 84-90
Author(s):  
R. Lalchhanhima ◽  
◽  
Debdatta Kandar ◽  
R. Chawngsangpuii ◽  
Vanlalmuansangi Khenglawt ◽  
...  
Keyword(s):  
Clustering Algorithm ◽  
State Of The Art ◽  
Speckle Noise ◽  
Synthetic Aperture Radar Image ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Spatial Filters ◽  
Fuzzy C Means ◽  
Automatic Clustering ◽  
Intensity Information

Fuzzy C-Means is an unsupervised clustering algorithm for the automatic clustering of data. Synthetic Aperture Radar Image Segmentation has been a challenging task because of the presence of speckle noise. Therefore the segmentation process can not directly rely on the intensity information alone but must consider several derived features in order to get satisfactory segmentation results. In this paper, it is attempted to use the fuzzy nature of classification for the purpose of unsupervised region segmentation in which FCM is employed. Different features are obtained by filtering of the image by using different spatial filters and are selected for segmentation criteria. The segmentation performance is determined by the accuracy compared with a different state of the art techniques proposed recently.

scholarly journals Sub-Diffraction Visible Imaging Using Macroscopic Fourier Ptychography and Regularization by Denoising

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3154 ◽  
Author(s):  
Zhixin Li ◽  
Desheng Wen ◽  
Zongxi Song ◽  
Gang Liu ◽  
Weikang Zhang ◽  
...  
Keyword(s):  
Phase Retrieval ◽  
State Of The Art ◽  
Imaging Technique ◽  
Speckle Noise ◽  
Laser Speckle ◽  
Coherent Imaging ◽  
Quantitative Metrics ◽  
Visible Imaging ◽  
Flow Algorithm ◽  
Diffraction Imaging

Imaging past the diffraction limit is of significance to an optical system. Fourier ptychography (FP) is a novel coherent imaging technique that can achieve this goal and it is widely used in microscopic imaging. Most phase retrieval algorithms for FP reconstruction are based on Gaussian measurements which cannot extend straightforwardly to long range, sub-diffraction imaging setup because of laser speckle noise corruption. In this work, a new FP reconstruction framework is proposed for macroscopic visible imaging. When compared with existing research, the reweighted amplitude flow algorithm is adopted for better signal modeling, and the Regularization by Denoising (RED) scheme is introduced to reduce the effects of speckle. Experiments demonstrate that the proposed method can obtain state-of-the-art recovered results on both visual and quantitative metrics without increasing computation cost, and it is flexible for real imaging applications.

Speckle Noise Filtering Using Back-Propagation Multi-Layer Perceptron Network in Synthetic Aperture Radar Image

2020 ◽  
pp. 489-510
Author(s):  
Khwairakpam Amitab ◽  
Debdatta Kandar ◽  
Arnab K. Maji
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Synthetic Aperture Radar ◽  
Back Propagation ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Multi Layer Perceptron ◽  
Sar Images ◽  
Artificial Neural

Synthetic Aperture Radar (SAR) are imaging Radar, it uses electromagnetic radiation to illuminate the scanned surface and produce high resolution images in all-weather condition, day and night. Interference of signals causes noise and degrades the quality of the image, it causes serious difficulty in analyzing the images. Speckle is multiplicative noise that inherently exist in SAR images. Artificial Neural Network (ANN) have the capability of learning and is gaining popularity in SAR image processing. Multi-Layer Perceptron (MLP) is a feed forward artificial neural network model that consists of an input layer, several hidden layers, and an output layer. We have simulated MLP with two hidden layer in Matlab. Speckle noises were added to the target SAR image and applied MLP for speckle noise reduction. It is found that speckle noise in SAR images can be reduced by using MLP. We have considered Log-sigmoid, Tan-Sigmoid and Linear Transfer Function for the hidden layers. The MLP network are trained using Gradient descent with momentum back propagation, Resilient back propagation and Levenberg-Marquardt back propagation and comparatively evaluated the performance.

Robust and discriminative dictionary learning for face recognition

2018 ◽  
Vol 16 (02) ◽  
pp. 1840004 ◽  
Author(s):  
Guojun Lin ◽  
Meng Yang ◽  
Linlin Shen ◽  
Mingzhong Yang ◽  
Mei Xie
Keyword(s):  
Face Recognition ◽  
Facial Expressions ◽  
Dictionary Learning ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Face Images ◽  
Proposed Model ◽  
Classification Capability ◽  
Discriminative Dictionary Learning

For face recognition, conventional dictionary learning (DL) methods have some disadvantages. First, face images of the same person vary with facial expressions and pose, illumination and disguises, so it is hard to obtain a robust dictionary for face recognition. Second, they don’t cover important components (e.g., particularity and disturbance) completely, which limit their performance. In the paper, we propose a novel robust and discriminative DL (RDDL) model. The proposed model uses sample diversities of the same face image to learn a robust dictionary, which includes class-specific dictionary atoms and disturbance dictionary atoms. These atoms can well represent the data from different classes. Discriminative regularizations on the dictionary and the representation coefficients are used to exploit discriminative information, which improves effectively the classification capability of the dictionary. The proposed RDDL is extensively evaluated on benchmark face image databases, and it shows superior performance to many state-of-the-art dictionary learning methods for face recognition.

scholarly journals Indoor Experiments of Bistatic/Multistatic GB-SAR with One-Stationary and One-Moving Antennae

2021 ◽  
Vol 13 (18) ◽  
pp. 3733
Author(s):  
Hoonyol Lee ◽  
Jihyun Moon
Keyword(s):  
Time Domain ◽  
Speckle Noise ◽  
The Other ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Sar Images ◽  
Airborne Sar ◽  
Transmitting Antenna ◽  
Azimuth Resolution ◽  
Ku Band

Ground-based synthetic aperture radar (GB-SAR) is a useful tool to simulate advanced SAR systems with its flexibility on RF system and SAR configuration. This paper reports an indoor experiment of bistatic/multistatic GB-SAR operated in Ku-band with two antennae: one antenna was stationary on the ground and the other was moving along a linear rail. Multiple bistatic GB-SAR images were taken with various stationary antenna positions, and then averaged to simulate a multistatic GB-SAR configuration composed of a moving Tx antenna along a rail and multiple stationary Rx antennae with various viewing angles. This configuration simulates the use of a spaceborne/airborne SAR system as a transmitting antenna and multiple ground-based stationary antennae as receiving antennae to obtain omni-directional scattering images. This SAR geometry with one-stationary and one-moving antennae configuration was analyzed and a time-domain SAR focusing algorithm was adjusted to this geometry. Being stationary for one antenna, the Doppler rate was analyzed to be half of the monostatic case, and the azimuth resolution was doubled. Image quality was enhanced by identifying and reducing azimuth ambiguity. By averaging multiple bistatic images from various stationary antenna positions, a multistatic GB-SAR image was achieved to have better image swath and reduced speckle noise.

Impact of Method Noise on SAR Image Despeckling

2020 ◽  
Vol 15 (1) ◽  
pp. 52-63 ◽  
Author(s):  
Prabhishek Singh ◽  
Raj Shree
Keyword(s):  
Performance Metrics ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Sar Images ◽  
Standard Methods ◽  
Residual Image ◽  
Method Noise ◽  
Image Despeckling ◽  
The Difference ◽  
And Performance

This article introduces the concept, use and implementation of method noise in the field of synthetic aperture radar (SAR) image despeckling. Method noise has the capability to enhance the efficiency and performance of any despeckling algorithm. It is easy, efficient and enhanced way of improving the results. The difference between speckled image and despeckled image contains some residual image information which is due to the inefficiency of the denoising algorithm. This article will compare the results of some standard methods with and without the use of method noise and prove its efficiency and validity. It also shows its best use in different ways of denoising. The results will be compared on the basis of performance metrics like PSNR and SSIM. The concept of method noise is not restricted to only SAR images. It has vast usage and application. It can be used in any denoising procedure such as medical images, optical image etc. but this paper shows the experimental results only on the SAR images.

scholarly journals Deep Cascade Generation on Point Sets

2019 ◽  
Author(s):  
Kaiqi Wang ◽  
Ke Chen ◽  
Kui Jia
Keyword(s):  
State Of The Art ◽  
Shape Reconstruction ◽  
The State ◽  
Graph Representation ◽  
Superior Performance ◽  
Point Sets ◽  
Single View ◽  
Proposed Model ◽  
3D Geometry ◽  
Low Dimensional

This paper proposes a deep cascade network to generate 3D geometry of an object on a point cloud, consisting of a set of permutation-insensitive points. Such a surface representation is easy to learn from, but inhibits exploiting rich low-dimensional topological manifolds of the object shape due to lack of geometric connectivity. For benefiting from its simple structure yet utilizing rich neighborhood information across points, this paper proposes a two-stage cascade model on point sets. Specifically, our method adopts the state-of-the-art point set autoencoder to generate a sparsely coarse shape first, and then locally refines it by encoding neighborhood connectivity on a graph representation. An ensemble of sparse refined surface is designed to alleviate the suffering from local minima caused by modeling complex geometric manifolds. Moreover, our model develops a dynamically-weighted loss function for jointly penalizing the generation output of cascade levels at different training stages in a coarse-to-fine manner. Comparative evaluation on the publicly benchmarking ShapeNet dataset demonstrates superior performance of the proposed model to the state-of-the-art methods on both single-view shape reconstruction and shape autoencoding applications.

Sign in / Sign up

Export Citation Format

Share Document