Recognition of occluded targets in SAR images based on matching of attributed scattering centers

2021 ◽  
Vol 12 (9) ◽  
pp. 932-943
Author(s):  
Chongzhen Lu ◽  
Xinsha Fu ◽  
Yue Lu
Keyword(s):  
Sar Images ◽  
Scattering Centers

Three-dimensional positions of scattering centers reconstruction from multiple SAR images based on radargrammetry

2015 ◽  
Vol 22 (5) ◽  
pp. 1776-1789 ◽  
Author(s):  
Jin-rong Zhong ◽  
Gong-jian Wen ◽  
Bing-wei Hui ◽  
De-ren Li
Keyword(s):  
Three Dimensional ◽  
Sar Images ◽  
Scattering Centers

scholarly journals Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network

2021 ◽  
Vol 13 (21) ◽  
pp. 4358
Author(s):  
Chuan Du ◽  
Lei Zhang
Keyword(s):  
Target Recognition ◽  
Automatic Target Recognition ◽  
Reconstruction Error ◽  
Sar Images ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Scattering Centers ◽  
Weak Scattering ◽  
Adversarial Examples ◽  
Adversarial Attack

Some recent articles have revealed that synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep learning are vulnerable to the attacks of adversarial examples and cause security problems. The adversarial attack can make a deep convolutional neural network (CNN)-based SAR-ATR system output the intended wrong label predictions by adding small adversarial perturbations to the SAR images. The existing optimization-based adversarial attack methods generate adversarial examples by minimizing the mean-squared reconstruction error, causing smooth target edge and blurry weak scattering centers in SAR images. In this paper, we build a UNet-generative adversarial network (GAN) to refine the generation of the SAR-ATR models’ adversarial examples. The UNet learns the separable features of the targets and generates the adversarial examples of SAR images. The GAN makes the generated adversarial examples approximate to real SAR images (with sharp target edge and explicit weak scattering centers) and improves the generation efficiency. We carry out abundant experiments using the proposed adversarial attack algorithm to fool the SAR-ATR models based on several advanced CNNs, which are trained on the measured SAR images of the ground vehicle targets. The quantitative and qualitative results demonstrate the high-quality adversarial example generation and excellent attack effectiveness and efficiency improvement.

scholarly journals Scattering centers monitoring in refocused SAR images on a high-resolution DEM

2014 ◽  
Author(s):  
Andrei Anghel ◽  
Gabriel Vasile ◽  
Cornel Ioana ◽  
Remus Cacoveanu ◽  
Silviu Ciochina ◽  
...  
Keyword(s):  
High Resolution ◽  
Sar Images ◽  
Scattering Centers

scholarly journals Scattering Centers Detection and Tracking in Refocused Spaceborne SAR Images for Infrastructure Monitoring

2015 ◽  
Vol 53 (8) ◽  
pp. 4379-4393 ◽  
Author(s):  
Andrei Anghel ◽  
Gabriel Vasile ◽  
Remus Cacoveanu ◽  
Cornel Ioana ◽  
Silviu Ciochina ◽  
...  
Keyword(s):  
Sar Images ◽  
Infrastructure Monitoring ◽  
Detection And Tracking ◽  
Scattering Centers

scholarly journals Scattering Characteristics of Targets above a Rough Surface in SAR Images

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Bo Zhao ◽  
Tie Jun Cui
Keyword(s):  
Rough Surface ◽  
Electromagnetic Scattering ◽  
Fourier Transforms ◽  
Coupling Effect ◽  
Frequency Method ◽  
Sar Images ◽  
X Band ◽  
Scattering Centers ◽  
Scattered Fields ◽  
Target Characteristics

The modeling, simulation, and analysis of target characteristics are essential to a synthetic aperture radar (SAR) image-based autotarget recognition (ATR) system. The coupling effect between targets and rough surface is also important to the electromagnetic scattering and remote sensing. In this work, the simulations to SAR images of targets above a finite rough surface have been investigated. The effect of rough surface on the target characteristics, or the coupling between the rough surface and targets, is analyzed in details by observing changes of locations and intensities of scattering centers in the SAR images. The SAR images are obtained by taking two-dimensional inverse fast Fourier transforms (FFTs) of the scattered fields, which are computed by the combined high-frequency method of shooting and bouncing ray (SBR) and truncated-wedge incremental-length diffraction coefficients (TW-ILDCs). Simulated results of SAR images for complicated targets above a rough surface are given under the 0.25 × 0.25 m2resolution at the X band, in which the coupling effect between targets and rough surface has been studied in details.

scholarly journals Spatially Diverse ISAR Imaging for Classification Performance Enhancement

2011 ◽  
Vol 57 (1) ◽  
pp. 15-21 ◽  
Author(s):  
Stefan Brisken ◽  
Dietmar Matthes ◽  
Torsten Mathy ◽  
Josef Worms
Keyword(s):  
Performance Enhancement ◽  
Target Identification ◽  
Classification Performance ◽  
Sar Images ◽  
Synchronization Errors ◽  
Aspect Angle ◽  
Scattering Centers ◽  
Isar Imaging ◽  
Spatially Distributed ◽  
Inverse Sar

Spatially Diverse ISAR Imaging for Classification Performance Enhancement One popular approach to the problem of Non-Cooperative Target Identification is the use of 2D Inverse SAR images. Methods to successfully identify a target include the comparison of a set of scattering centers in the ISAR image to a database or the estimation of target dimensions. While working well in theory, these techniques face major difficulties in practice. In the conventional case of a monostatic radar, visibility of scattering centers varies with the target aspect angle due to fading. In this paper we examine that the visibility of scattering centers can be improved by incoherent addition of images from spatially distributed radars. The main focus lies in the description and results of a multistatic ISAR experiment carried out at Fraunhofer FHR. We display theoretically derived bistatic synchronization errors in a practical system and formulate additional multistatic synchronization requirements, necessary to add up the images.

scholarly journals A Convolutional Neural Network Combined with Attributed Scattering Centers for SAR ATR

2021 ◽  
Vol 13 (24) ◽  
pp. 5121
Author(s):  
Yu Zhou ◽  
Yi Li ◽  
Weitong Xie ◽  
Lu Li
Keyword(s):  
Electromagnetic Scattering ◽  
Automatic Target Recognition ◽  
Image Features ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Sar Images ◽  
Stationary Target ◽  
Local Structures ◽  
Scattering Centers ◽  
High Level

It is very common to apply convolutional neural networks (CNNs) to synthetic aperture radar (SAR) automatic target recognition (ATR). However, most of the SAR ATR methods using CNN mainly use the image features of SAR images and make little use of the unique electromagnetic scattering characteristics of SAR images. For SAR images, attributed scattering centers (ASCs) reflect the electromagnetic scattering characteristics and the local structures of the target, which are useful for SAR ATR. Therefore, we propose a network to comprehensively use the image features and the features related to ASCs for improving the performance of SAR ATR. There are two branches in the proposed network, one extracts the more discriminative image features from the input SAR image; the other extracts physically meaningful features from the ASC schematic map that reflects the local structure of the target corresponding to each ASC. Finally, the high-level features obtained by the two branches are fused to recognize the target. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset prove the capability of the SAR ATR method proposed in this letter.

Sign in / Sign up

Export Citation Format

Share Document