RBM‐based joint dictionary learning for ISAR resolution enhancement

Autor: Dan Qin, Xunzhang Gao, Jiaqi Ye, Yifan Zhang
Rok vydání: 2019
Předmět:
Synthetic aperture radar
similar sparse representation coefficients
image patches
joint dictionary learning
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Energy Engineering and Power Technology
Iterative reconstruction
coupled dictionary learning algorithm
restricted boltzmann machine
hr dictionary
similar scattering-centre models
image enhancement
image representation
lr dictionary
classical dictionary training algorithms
sparse signals
Image resolution
dictionaries
radar signals
Restricted Boltzmann machine
business.industry
Resolution (electron density)
General Engineering
boltzmann machines
rbm-based joint dictionary
Pattern recognition
image reconstruction
radar imaging
isar resolution enhancement
Inverse synthetic aperture radar
inverse synthetic aperture radar image resolution enhancement algorithm
lcsh:TA1-2040
Computer Science::Computer Vision and Pattern Recognition
hr isar image
lr isar image shares
learning (artificial intelligence)
Artificial intelligence
lcsh:Engineering (General). Civil engineering (General)
Joint (audio engineering)
business
Dictionary learning
Software
image resolution
synthetic aperture radar
Zdroj: The Journal of Engineering (2019)
ISSN: 2051-3305
DOI: 10.1049/joe.2019.0732
Popis: In this study, an inverse synthetic aperture radar (ISAR) image resolution enhancement algorithm based on joint dictionary learning is proposed, by which two special sets of sparse signals called dictionaries are solved by exploiting numerous high-resolution (HR) and low-resolution (LR) ISAR images. Herein a new coupled dictionary learning algorithm based on restricted Boltzmann machine (RBM) is designed to learn a LR and a HR dictionary using LR and HR image patches. Since the echoes are equivalent to similar scattering-centre models when an object is illuminated by radar signals with same centre frequency and different bandwidth, respectively, it is reasonable to assume the object's LR ISAR image shares the same sparse representation coefficients with its HR ISAR image. When a LR ISAR image is represented sparsely with a LR dictionary, a HR ISAR images can be reconstructed based on a HR dictionary owing to the similar sparse representation coefficients. Experiment results with simulation data demonstrate the superior performance of the proposed method over other classical dictionary training algorithms.
Databáze: OpenAIRE
Externí odkaz: