Convolutional neural networks for synthetic aperture radar classification

Profeta, Andrew; Rodríguez, Andrés; Clouse, Hamilton Scott

doi:10.1117/12.2225934

Cited by 26 publications

(19 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CNN are especially appealing for our application due to their ability to capture invariants [31,32], reduce dimensionality from noisy data [33], and classify objects [34]. Initial uses of data driven approaches for imaging problems have been suggested in microscopy [35], compressive imaging [36], synthetic aperture radar [37], remote sensing [38,39], dehazing [40], phase imaging [41], medical imaging [42], and classification with coherent light [44,43]. In our case the CNN is trained with synthesized data that includes variations in calibration parameters.…”

Section: Introductionmentioning

confidence: 99%

Object classification through scattering media with deep learning on time resolved measurement

Satat¹,

Tancik²,

Gupta³

et al. 2017

Opt. Express

127

View full text Add to dashboard Cite

We demonstrate an imaging technique that allows identification and classification of objects hidden behind scattering media and is invariant to changes in calibration parameters within a training range. Traditional techniques to image through scattering solve an inverse problem and are limited by the need to tune a forward model with multiple calibration parameters (like camera field of view, illumination position etc.). Instead of tuning a forward model and directly inverting the optical scattering, we use a data driven approach and leverage convolutional neural networks (CNN) to learn a model that is invariant to calibration parameters variations within the training range and nearly invariant beyond that. This effectively allows robust imaging through scattering conditions that is not sensitive to calibration. The CNN is trained with a large synthetic dataset generated with a Monte Carlo (MC) model that contains random realizations of major calibration parameters. The method is evaluated with a time-resolved camera and multiple experimental results are provided including pose estimation of a mannequin hidden behind a paper sheet with 23 correct classifications out of 30 tests in three poses (76.6% accuracy on real-world measurements). This approach paves the way towards real-time practical non line of sight (NLOS) imaging applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Object classification through scattering media with deep learning on time resolved measurement

Satat¹,

Tancik²,

Gupta³

et al. 2017

Opt. Express

127

View full text Add to dashboard Cite

show abstract

“…In subsequent studies, it is planned to apply boosting algorithms, such as AdaBoost [9], and neural networks. Over the past few years, there have been many publications using neural networks [10] for the classification of radar images, so their study and comparison of classification results with the results obtained in this paper is of great interest.…”

Section: Resultsmentioning

confidence: 98%

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base

Borodinov¹,

Myasnikov²

2017

Collection of Selected Papers of the III International Conference on Information Technology and Nanotechnology

View full text Add to dashboard Cite

The present work is devoted to the analysis of local objects on radar images. In comparison, the following algorithms are used: decision tree; Bayesian classifier for normal distribution; Nearest neighbor method; Support Vector Method (SVM). As preliminary processing of images provided by a synthetic aperture radar. The research is carried out on the objects from the base of radar images MSTAR. The paper presents the results of the conducted studies.

show abstract

“…In the context of SAR ATR, literature suggests several CNN based solutions that rely on handcrafted CNNs [5], [7], [8], [12], [13]. A common feature of these CNN architectures is their relatively low depth that varies from six up to nine layers, opposing to the mainstream visual domain CNNs where layers are 23 for AlexNet [32], 16 or 19 for VGG [33] depending on the version, 22 for GoogleNet [34] and 152 for ResNet [35].…”

Section: B Clustered Convolutional Neural Networkmentioning

confidence: 99%

“…Deep Convolutional Neural Networks (CNNs) have also been suggested for SAR ATR. Literature proposes several CNN based solutions that use handcrafted CNNs [5], [8], [12], [13], [30] that are trained on SAR template images. Recently a Recurrent Neural Network is also suggested [31].…”

Section: Introduction Odern Warfare Requires High Performing Autommentioning

confidence: 99%

Fusing Deep Learning and Sparse Coding for SAR ATR

Kechagias‐Stamatis

Aouf

2019

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

We propose a multi-modal and multi-discipline data fusion strategy appropriate for Automatic Target Recognition (ATR) on Synthetic Aperture Radar imagery. Our architecture fuses a proposed Clustered version of the AlexNet Convolutional Neural Network with Sparse Coding theory that is extended to facilitate an adaptive elastic net optimization concept. Evaluation on the MSTAR dataset yields the highest ATR performance reported yet which is 99.33% and 99.86% for the 3 and 10-class problems respectively.

show abstract

Convolutional neural networks for synthetic aperture radar classification

Cited by 26 publications

References 5 publications

Object classification through scattering media with deep learning on time resolved measurement

Object classification through scattering media with deep learning on time resolved measurement

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base

Fusing Deep Learning and Sparse Coding for SAR ATR

Contact Info

Product

Resources

About