Feature-Supervised Compressed Sensing for Microwave Imaging Systems

Tang, Chaoqing; Tian, Gui Yun; Boussakta, S.; Wu, Jianbo

doi:10.1109/tim.2019.2962562

Cited by 10 publications

(4 citation statements)

References 46 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing works [ 27 , 28 ], show that there are some resonant frequency bands that review impact damages better, i.e., 18.86 GHz, 20.65 GHz, and etc. The amplitudes of reflection coefficients are used for imaging.…”

Section: Resultsmentioning

confidence: 99%

“…The hardware-based efficiency improvement methods will increase the cost with more sensors, an alternative is using compressed sensing (CS) to reduce the acquisition points without a hardware update. Tang et al [ 27 , 28 , 29 ], propose CS based methods on NRI systems for impact damage detection on CFRPs which greatly reduces the measurement time. CS [ 30 , 31 ], reduces the acquisition data greatly by measuring the linear weightings of an imaging scene.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing

et al. 2022

Self Cite

View full text Add to dashboard Cite

Carbon fiber-reinforced polymer (CFRP) is a widely-used composite material that is vulnerable to impact damage. Light impact damages destroy the inner structure but barely show obvious change on the surface. As a non-contact and high-resolution method to detect subsurface and inner defect, near-field radiofrequency imaging (NRI) suffers from high imaging times. Although some existing works use compressed sensing (CS) for a faster measurement, the corresponding CS reconstruction time remains high. This paper proposes a deep learning-based CS method for fast NRI, this plugin method decreases the measurement time by one order of magnitude without hardware modification and achieves real-time imaging during CS reconstruction. A special 0/1-Bernoulli measurement matrix is designed for sensor scanning firstly, and an interpretable neural network-based CS reconstruction method is proposed. Besides real-time reconstruction, the proposed learning-based reconstruction method can further reduce the required data thus reducing measurement time more than existing CS methods. Under the same imaging quality, experimental results in an NRI system show the proposed method is 20 times faster than traditional raster scan and existing CS reconstruction methods, and the required data is reduced by more than 90% than existing CS reconstruction methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Invisible impact damages on CFRP greatly influence the strength and lead to safety risks. Near-field microwave imaging is one common technology that is used for invisible impact damage detection, but current methods only use raster scan or traditional iterative reconstruction methods [34,35], which take hours to perform detection.…”

Section: Application In Near-field Microwave Imagingmentioning

confidence: 99%

“…Deep learning methods can learn this prior information from the training datasets and are able to handle multiple kinds of noise at the same time [26]. Deep learning also has the potential for task processing during reconstruction; this has recently emerged up in traditional CS reconstruction [34,35].…”

Section: Introductionmentioning

confidence: 99%

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Chen,

Song,

Zeng

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

Compressed sensing (CS) is a popular data compression theory for many computer vision tasks, but the high reconstruction complexity for images prevents it from being used in many real-world applications. Existing end-to-end learning methods achieved real time sensing but lack theory guarantee for robust reconstruction results. This paper proposes a neural network called RootsNet, which integrates the CS mechanism into the network to prevent error propagation. So, RootsNet knows what will happen if some modules in the network go wrong. It also implements real-time and successfully reconstructed extremely low measurement rates that are impossible for traditional optimization-theory-based methods. For qualitative validation, RootsNet is implemented in two real-world measurement applications, i.e., a near-field microwave imaging system and a pipeline inspection system, where RootsNet easily saves 60% more measurement time and 95% more data compared with the state-of-the-art optimization-theory-based reconstruction methods. Without losing generality, comprehensive experiments are performed on general datasets, including evaluating the key components in RootsNet, the reconstruction uncertainty, quality, and efficiency. RootsNet has the best uncertainty performance and efficiency, and achieves the best reconstruction quality under super low-measurement rates.

show abstract

Confidence based compressed sensing approach with QoS differentiation for reliable grant-free access

Luo,

Dang,

Wei

2024

Expert Systems with Applications

View full text Add to dashboard Cite

Feature-Supervised Compressed Sensing for Microwave Imaging Systems

Cited by 10 publications

References 46 publications

Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing

Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Confidence based compressed sensing approach with QoS differentiation for reliable grant-free access

Contact Info

Product

Resources

About