scholarly journals High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

2021 ◽  
Vol 13 (12) ◽  
pp. 2326
Author(s):  
Xiaoyong Li ◽  
Xueru Bai ◽  
Feng Zhou
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Phase Error ◽  
Random Phase ◽  
Back Propagation ◽  
Estimation Method ◽  
Data Driven ◽  
Reconstruction Performance ◽  
Imaging Results ◽  
Isar Imaging

A deep-learning architecture, dubbed as the 2D-ADMM-Net (2D-ADN), is proposed in this article. It provides effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging under scenarios of low SNRs and incomplete data, by combining model-based sparse reconstruction and data-driven deep learning. Firstly, mapping from ISAR images to their corresponding echoes in the wavenumber domain is derived. Then, a 2D alternating direction method of multipliers (ADMM) is unrolled and generalized to a deep network, where all adjustable parameters in the reconstruction layers, nonlinear transform layers, and multiplier update layers are learned by an end-to-end training through back-propagation. Since the optimal parameters of each layer are learned separately, 2D-ADN exhibits more representation flexibility and preferable reconstruction performance than model-driven methods. Simultaneously, it is able to better facilitate ISAR imaging with limited training samples than data-driven methods owing to its simple structure and small number of adjustable parameters. Additionally, benefiting from the good performance of 2D-ADN, a random phase error estimation method is proposed, through which well-focused imaging can be acquired. It is demonstrated by experiments that although trained by only a few simulated images, the 2D-ADN shows good adaptability to measured data and favorable imaging results with a clear background can be obtained in a short time.

scholarly journals Research on Turning Motion Targets and Velocity Estimation in High Resolution Spaceborne SAR

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2201 ◽  
Author(s):  
Xuejiao Wen ◽  
Xiaolan Qiu
Keyword(s):  
High Resolution ◽  
Geometric Modeling ◽  
Phase Error ◽  
Estimation Method ◽  
Velocity Estimation ◽  
Continuous Change ◽  
Straight Line ◽  
Moving Direction ◽  
Turning Motion ◽  
Motion Imaging

The development of high resolution SAR makes the influence of moving target more prominent, which results in defocusing and other unexplained phenomena. This paper focuses on the research of imaging signatures and velocity estimation of turning motion targets. In this paper, the turning motion is regarded as the straight line motion of continuous change of moving direction. Through the analysis of the straight line motion with constant velocity and the geometric modeling of the turning motion in spaceborne SAR, the imaging signatures of the turning motion target are obtained, such as the broken line phenomenon at the curve. Furthermore, a method for estimating the turning velocity is proposed here. The radial velocity is calculated by the azimuth offset of the turning motion target and the azimuth velocity is calculated by the phase error compensated in the refocusing process. The amplitude and direction of the velocity can be obtained by using both of them. The results of simulation and GF-3 data prove the accuracy of the analysis of turning motion imaging signatures, and they also show the accuracy and validity of the velocity estimation method in this paper.

scholarly journals Ground-Based Solar Absorption FTIR Spectroscopy: Characterization of Retrievals and First Results from a Novel Optical Design Instrument at a New NDACC Complementary Station

2007 ◽  
Vol 24 (3) ◽  
pp. 432-448 ◽  
Author(s):  
A. Wiacek ◽  
J. R. Taylor ◽  
K. Strong ◽  
R. Saari ◽  
T. E. Kerzenmacher ◽  
...  
Keyword(s):  
High Resolution ◽  
Stratospheric Ozone ◽  
Phase Error ◽  
Optical Design ◽  
Estimation Method ◽  
Optical Path Difference ◽  
Atmospheric Composition ◽  
Retrieval Algorithm ◽  
Atmospheric Measurements ◽  
Solar Absorption

Abstract The authors describe the optical design of a high-resolution Fourier Transform Spectrometer (FTS), which serves as the primary instrument at the University of Toronto Atmospheric Observatory (TAO). The FTS is dedicated to ground-based infrared solar absorption atmospheric measurements from Toronto, Ontario, Canada. Instrument performance is discussed in terms of instrumental line shape (ILS) and phase error and modulation efficiency as a function of optical path difference. Typical measurement parameters are presented together with retrieval parameters used to derive total and partial column concentrations of ozone. Retrievals at TAO employ the optimal estimation method (OEM), and some impacts of the necessary a priori constraints are examined. In March 2004, after participating in a retrieval algorithm user intercomparison exercise, the TAO FTS was granted the status of a Complementary Observation Station within the international community of high-resolution FTS users in the Network for the Detection of Atmospheric Composition and Change (NDACC). During this exercise, average differences between total columns retrieved from the same spectra by different users were below 2.1% for O3, HCl, and N2O in the blind phase, and below 1% in the open phase, when all retrieval constraints were identical. Finally, a 2.5-yr time series of monthly mean stratospheric ozone columns agrees within 3% with those retrieved from Optical Spectrograph and Infrared Imager System (OSIRIS) measurements on board the Odin satellite, which is within the errors of both measurement platforms.

scholarly journals A New Rang-Instantaneous Doppler ISAR Imaging Algorithm

2012 ◽  
Vol 6-7 ◽  
pp. 682-687
Author(s):  
Bao Ping Wang ◽  
Chao Sun ◽  
Jun Jie Guo
Keyword(s):  
High Resolution ◽  
Sparse Representation ◽  
Motion Compensation ◽  
Noise Suppression ◽  
Phase Error ◽  
Doppler Imaging ◽  
Imaging Algorithm ◽  
Time Frequency ◽  
Maneuvering Target ◽  
Isar Imaging

ISAR imaging algorithm based on sparse representation has the advantages of high resolution, noise suppression and dealing with gapped data effectively. The method is based on the hypothesis that the imaging targets move smoothly. But the movement of ISAR imaging targets is usually of high maneuverability, which results in big phase error after motion compensation. Using the traditional RD imaging algorithm and the imaging algorithm based on sparse representation will make the resultant image fuzzy, and can't even be identified. This paper introduces a new range- instantaneous Doppler imaging algorithm based on sparse representation and time-frequency transform, which can effectively image the maneuvering target. The experimental results validate the feasibility of this approach.

Deep learning-enhanced single point sound source localization for spherical microphone array

2021 ◽  
Vol 263 (4) ◽  
pp. 2279-2283
Author(s):  
Soo Young Lee ◽  
Jiho Chang ◽  
Seungchul Lee
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
High Resolution ◽  
Source Localization ◽  
Sound Source ◽  
Single Point ◽  
Data Driven ◽  
Sound Source Localization ◽  
Localization Model ◽  
Source Localization Model

In this contribution, we present a high-resolution and accurate sound source localization via a deep learning framework. While the spherical microphone arrays can be utilized to produce omnidirectional beams, it is widely known that the conventional spherical harmonics beamforming (SHB) has a limit in terms of its spatial resolution. To accomplish the sound source localization with high resolution and preciseness, we propose a convolutional neural network (CNN)-based source localization model as a way of a data-driven approach. We first present a novel way to define the source distribution map that can spatially represent the single point source's position and strength. By utilizing paired dataset with spherical harmonics beamforming maps and our proposed high-resolution maps, we develop a fully convolutional neural network based on the encoder-decoder structure for establishing the image-to-image transformation model. Both quantitative and qualitative results are demonstrated to evaluate the powerfulness of the proposed data-driven source localization model.

scholarly journals An Iterative Phase Autofocus Approach for ISAR Imaging of Maneuvering Targets

Electronics ◽  
2021 ◽  
Vol 10 (17) ◽  
pp. 2100
Author(s):  
Binbin Wang ◽  
Hao Cha ◽  
Zibo Zhou ◽  
Huatao Tang ◽  
Lidong Sun ◽  
...  
Keyword(s):  
Simple Procedure ◽  
Phase Error ◽  
Translational Motion ◽  
Minimum Entropy ◽  
New Approach ◽  
Maneuvering Targets ◽  
Quadratic Phase ◽  
Imaging Results ◽  
Isar Imaging ◽  
Maneuvering Motion

Translational motion compensation and azimuth compression are two essential processes in inverse synthetic aperture radar (ISAR) imaging. The anterior process recovers coherence between pulses, during which the phase autofocus algorithm is usually used. For ISAR imaging of maneuvering targets, conventional phase autofocus methods cannot effectively eliminate the phase error due to the adverse influence of the quadratic phase terms caused by the target’s maneuvering motion, which leads to the blurring of ISAR images. To address this problem, an iterative phase autofocus approach for ISAR imaging of maneuvering targets is proposed in this paper. Considering the coupling between translational phase errors and quadratic phase terms, minimum entropy-based autofocus (MEA) method and adaptive modified Fourier transform (MFT) are performed iteratively to realize better imaging results. In this way, both the translational phase error and quadratic phase terms induced by target’s maneuvering motion can be compensated effectively, and the globally optimal ISAR image is obtained. Comparison ISAR imaging results indicates that the new approach achieves stable and better ISAR image under a simple procedure. Experimental results show that the image entropy of the proposed approach is 0.2 smaller than the MEA method, which validates the effectiveness of the new approach.

scholarly journals AHLF: ad hoc learning of fragmentation patterns in mass spectra detects post-translationally modified peptides prior to database search

2020 ◽  
Author(s):  
Tom Altenburg ◽  
Shengbo Wang ◽  
Thilo Muth ◽  
Bernhard Y. Renard
Keyword(s):  
Deep Learning ◽  
Mass Spectrum ◽  
High Resolution ◽  
Mass Spectra ◽  
Ad Hoc ◽  
Data Driven ◽  
High Resolution Spectrum ◽  
Tandem Mass ◽  
End To End ◽  
Fragmentation Patterns

AbstractMotivationPublicly available mass spectrometry-based proteomics data has grown exponentially in the recent past. Yet, large scale spectrum-centered analysis usually involves predefined fragmentation features that are limited and prone to be biased. Using deep learning, the decision making for a suitable fragmentation model can be carried out in a data-driven manner.ResultsWe introduce a framework that allows end-to-end training of generic deep learning models on a large collection of high resolution tandem mass spectra. In this case we used 19.2 million labeled spectra from more than a hundred individual PRIDE repositories. In our framework, we developed a representation that captures the complete information of a high-resolution spectrum facilitating a loss-less reduction of the number of features largely independent of the actual resolution. Additionally, it allows us to use common trainable layers, e.g. recurrent or convolutional operations. Specifically, we use a deep network of stacked dilated convolutions to model long range associations between any peaks within a tandem mass spectrum. We exemplify our approach by learning to detect post-translational modifications – in this case, protein phosphorylation – only based on a given mass spectrum in a fully data-driven manner. To the best of our knowledge, this is the first end-to-end trained deep learning model on tandem spectra that is able to ad hoc learn fragmentation patterns in high-resolution spectra. Our approach outperforms the current state-of-the-art in predicting if a mass spectrum originates from a phosphorylated peptide.AvailabilityOur deep learning framework is implemented in tensorflow. The open source code including trained weights is available at gitlab.com/dacs-hpi/[email protected]

An Anatomy of a Hybrid Color Descriptor with a Neural Network Model to Enhance the Retrieval Accuracy of an Image Retrieval System

2019 ◽  
Vol 13 ◽  
Author(s):  
Shikha Bhardwaj ◽  
Gitanjali Pandove ◽  
Pawan Kumar Dahiya
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Retrieval ◽  
Hybrid System ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Retrieval Accuracy ◽  
Color Descriptor ◽  
Benchmark Datasets ◽  
Color Moment

Background: In order to retrieve a particular image from vast repository of images, an efficient system is required and such an eminent system is well-known by the name Content-based image retrieval (CBIR) system. Color is indeed an important attribute of an image and the proposed system consist of a hybrid color descriptor which is used for color feature extraction. Deep learning, has gained a prominent importance in the current era. So, the performance of this fusion based color descriptor is also analyzed in the presence of Deep learning classifiers. Method: This paper describes a comparative experimental analysis on various color descriptors and the best two are chosen to form an efficient color based hybrid system denoted as combined color moment-color autocorrelogram (Co-CMCAC). Then, to increase the retrieval accuracy of the hybrid system, a Cascade forward back propagation neural network (CFBPNN) is used. The classification accuracy obtained by using CFBPNN is also compared to Patternnet neural network. Results: The results of the hybrid color descriptor depict that the proposed system has superior results of the order of 95.4%, 88.2%, 84.4% and 96.05% on Corel-1K, Corel-5K, Corel-10K and Oxford flower benchmark datasets respectively as compared to many state-of-the-art related techniques. Conclusion: This paper depict an experimental and analytical analysis on different color feature descriptors namely, Color moment (CM), Color auto-correlogram (CAC), Color histogram (CH), Color coherence vector (CCV) and Dominant color descriptor (DCD). The proposed hybrid color descriptor (Co-CMCAC) is utilized for the withdrawal of color features with Cascade forward back propagation neural network (CFBPNN) is used as a classifier on four benchmark datasets namely Corel-1K, Corel-5K and Corel-10K and Oxford flower.

scholarly journals High-Resolution Photoabsorption Spectrum of Cs+ (5p61So + 5p5ns, nd) Between 504A and 600A using a Laser Ionized Cs Vapor Column

1984 ◽  
Vol 86 ◽  
pp. 124-124
Author(s):  
T.J. McIlrath ◽  
V. Kaufman ◽  
J. Sugar ◽  
W.T. Hill ◽  
D. Cooper
Keyword(s):  
High Resolution ◽  
Laser Pulse ◽  
High Voltage ◽  
Power Output ◽  
Random Phase ◽  
Grazing Incidence ◽  
Fano Resonances ◽  
Line Shapes ◽  
Phase Calculation ◽  
Photoabsorption Spectrum

Rapid ionization of Cs vapor in a heat pipe at 0.05 torr was achieved by pumping the 6s 2S½ – 7p 2P½ transition (f=0.007)1 with a flash-pumped dye laser at 4593.2A and I MW power output. Photoabsorptian initiated at the end of the laser pulse(≃ 0.5/s) showed the 5p5ns and nd series below and above the 5p52P3/2 threshold at 535.4A. Broad Beutler - Fano resonances appeared in the d series above threshold. The spectrum was recorded photographically on a 10.7m grazing incidence spectrograph using a continuum background generated by a BRV high-voltage spark source with a uranium anode. We will compare the line-shapes and the quantum defect (Lu-Fano2) plot with the predictions of a relativistic random phase calculation.

Sign in / Sign up

Export Citation Format

Share Document