Pattern Coupled Sparse Bayesian Learning Based on UTAMP for Robust High Resolution ISAR Imaging

Kang, Hailong; Li, Jun; Guo, Qinghua

doi:10.1109/jsen.2020.3004037

Cited by 18 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Message Computations in Subgraph 1: In this subgraph, we only need to compute the outgoing (forward) messages {m β→fr m (β)}, which are input to Subgraph 2. The derivation of the message update rule is delayed in the message computations in Subgraph 2, and is given in (29).…”

Section: B Derivation Of Uamp-sbl With Svmpmentioning

confidence: 99%

“…In addition, we extend the UAMP-SBL algorithm from single measurement vector (SMV) problems to multiple measurement vector (MMV) problems [25], [26], [27]. Based on our preliminary results in [28], UAMP-SBL has been applied to inverse synthetic aperture radar (ISAR) [29], where the measurement matrix is highly correlated in order to achieve high Doppler resolution. Real data experiments in [29] demonstrate its superiority in terms of both recovery performance and speed.…”

Section: Introductionmentioning

confidence: 99%

“…Based on our preliminary results in [28], UAMP-SBL has been applied to inverse synthetic aperture radar (ISAR) [29], where the measurement matrix is highly correlated in order to achieve high Doppler resolution. Real data experiments in [29] demonstrate its superiority in terms of both recovery performance and speed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unitary Approximate Message Passing for Sparse Bayesian Learning

Luo¹,

Guo²,

Jin³

et al. 2021

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm. However, it is vulnerable to 'difficult' measurement matrices, which may cause AMP to diverge. Damped AMP has been used for SBL to alleviate the problem at the cost of reducing convergence speed. In this work, we propose a new SBL algorithm based on structured variational inference, leveraging AMP with a unitary transformation (UAMP). Both single measurement vector and multiple measurement vector problems are investigated. It is shown that, compared to stateof-the-art AMP-based SBL algorithms, the proposed UAMP-SBL is more robust and efficient, leading to remarkably better performance.

show abstract

Section: B Derivation Of Uamp-sbl With Svmpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unitary Approximate Message Passing for Sparse Bayesian Learning

Luo¹,

Guo²,

Jin³

et al. 2021

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Reference [365] presents comparisons between CS and other super-resolution techniques in ISAR. A number of different CS methods have been used for this purpose: sparse Bayesian learning [366]- [373], the RELAX method [374], matching pursuit [375], and dictionary learning [376], [377].…”

Section: A Cs In Isarmentioning

confidence: 99%

Inverse Synthetic Aperture Radar Imaging: A Historical Perspective and State-of-the-Art Survey

Vehmas¹,

Neuberger

2021

IEEE Access

View full text Add to dashboard Cite

Radar can obtain high spatial resolution at large operating distances and its operation is largely independent from weather and lighting conditions. This makes it an important instrument in an ever-increasing number of applications requiring robust and reliable sensing of the environment. Due to the advancements in semiconductor technology and digital computation power, radar can obtain increasingly better position estimation accuracy, detection sensitivity, and target resolution. High-resolution imaging is an example of a rapidly advancing field of radar technology. Inverse synthetic aperture radar (ISAR) is an imaging technique that uses the motion of a target to obtain a high-resolution radar image of it. This paper presents a comprehensive review of past work and the state-of-the-art in ISAR imaging systems, algorithms, and applications. Starting from the early historical developments of simple monostatic range-Doppler imaging, we present the developments up to the current advanced spatially distributed imaging modalities and reconstruction algorithms. The list of references includes the most influential ISAR publications in the open literature up to early 2021.

show abstract

“…UTAMP was also recently employed for sparse Bayesian learning (SBL) [17], and it shows outstanding performance even with difficult measurement matrices. The application of UTAMP to inverse synthetic aperture radar (ISAR) imaging was also studied, and real data experiments show its excellent capability to achieve high Doppler resolution with low complexity, where the measurement matrix can be highly correlated to achieve high Doppler resolution [18]. These motivated the work in this paper to design robust message passing bilinear recovery algorithms with UTAMP.…”

Section: Introductionmentioning

confidence: 99%

Approximate Message Passing With Unitary Transformation for Robust Bilinear Recovery

Yuan

Guo

Luo

2021

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Recently, several promising approximate message passing (AMP) based algorithms have been developed for bilinear recovery with model Y = K k=1 b k A k C + W , where {b k } and C are jointly recovered with known A k from the noisy measurements Y . The bilinear recover problem has many applications such as dictionary learning, self-calibration, compressive sensing with matrix uncertainty, etc. In this work, we propose a new bilinear recovery algorithm based on AMP with unitary transformation and hybrid message passing. It is shown that, compared to the state-of-the-art message passing based algorithms, the proposed algorithm is much more robust and faster, leading to remarkably better performance.

show abstract

Pattern Coupled Sparse Bayesian Learning Based on UTAMP for Robust High Resolution ISAR Imaging

Cited by 18 publications

References 27 publications

Unitary Approximate Message Passing for Sparse Bayesian Learning

Unitary Approximate Message Passing for Sparse Bayesian Learning

Inverse Synthetic Aperture Radar Imaging: A Historical Perspective and State-of-the-Art Survey

Approximate Message Passing With Unitary Transformation for Robust Bilinear Recovery

Contact Info

Product

Resources

About