A Novel Sea Clutter Suppression Method Based on Deep Learning with Exploiting Time-Frequency Features

Tang, Xianhui; Dong, Li; Cheng, Wanru; Su, Jia; Wan, Jun

doi:10.1109/iaeac50856.2021.9390660

Cited by 10 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the intrinsic properties of sea clutter are extremely complex, and it is difficult to describe them comprehensively in a single theoretical model. Recently, with the development of artificial intelligence (AI) technology, there are increasing researches to translate the weak target detection problem into target and clutter classification problem (Chen et al, 2021; Dai et al, 2021; Fan et al, 2020; Ma et al, 2020; Tang et al, 2021). The high‐dimensional feature space combined with multiple features of sea clutter can effectively combine the sea surface weak target detection problem with advanced AI technology to identify the target.…”

Section: Related Workmentioning

confidence: 99%

Marine radar monitoring IoT system and case study of target detection based on PPI images

Zhang

Guo

et al. 2023

Expert Systems

View full text Add to dashboard Cite

To ensure the ship navigation safety, it is necessary to detect the targets in the background of sea clutter around the ship. The most commonly used target detection equipments for ship navigation are marine radar and automatic identification system (AIS) device. However, marine radar echoes are often mixed with multiple clutter, and weak targets are not always equipped with AIS device, neither provides AIS information with low accuracy, leading to difficulty with target detection. Moreover, existing marine monitoring systems are accustomed to using the traditional information fusion methods for target detection, and the accuracy of identifying the weak targets is relatively low. To make full use of radar echo and AIS information and improve the accuracy of target detection, a Marine radar monitoring Internet of Things system is proposed, in which marine radars work in both scanning and staring modes. By adopting image segmentation and deep learning methods, the proposed design can enable accurate perception of weak target detection based on plan‐position indicator (PPI) images. A case study based on the selected X‐band radar datasets shows that the proposed design can achieve high target identification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Marine radar monitoring IoT system and case study of target detection based on PPI images

Zhang

Guo

et al. 2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Thus, cGANs exhibit a great potential to tailor the processing of SAR images so that cleaner images can be generated from those ones contaminated with artifacts caused by complex imaging scenarios (e.g., multilayered scenarios), the additional challenges from some novel advanced SAR systems (e.g., irregular sampling), and some of the inherent limitations of SAR processing. To the best authors knowledge, although some deep learning approaches have been applied to the classification of targets in conventional radar approaches [29], [30] and to reduce the sea clutter [31], their application to clean high-resolution images coming from modern inspection systems based on near-field SAR has not been studied. In this paper, cGANs are adapted to improve the quality of near-field SAR images prone to artifacts.…”

Section: Introductionmentioning

confidence: 99%

Artifact Mitigation for High-Resolution Near-Field SAR Images by Means of Conditional Generative Adversarial Networks

Laviada

Álvarez-Narciandi

Las-Heras

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

This work presents an approach to enhance the quality of high-resolution images obtained by means of systems relying on synthetic aperture radar (SAR). For this purpose, a deep learning method called conditional generative adversarial networks (cGAN) is applied to the imager outcome when it is prone to suffer artifacts. This is specially the case of novel systems pushing the limits of SAR (e.g., irregular sampling, multilayered media, etc.) resulting in very chaotic clutter and image artifacts that cannot be easily removed with conventional approaches. The cGAN can be trained to detect high-level characteristic features in the image (e.g., parts of a scissor blade) so another output based on these detected features can be tailored. In other words, it can translate features contaminated by artifacts into clean features, effectively improving the quality of SAR images. Unlike other deep learning approaches, the training of the involved neural networks tends to be stable thanks to the structure based on two competing subsystems. The proposed approach is illustrated using simulated and measurement data in the context of two advanced near-field SAR systems considering: i) cylindrical multilayered media, and ii) freehand acquisitions. Results show that cGANs clearly outperform conventional approaches removing most of the artifacts, enabling to produce a clean output image.

show abstract

Lightweight deep neural network for radio frequency interference detection and segmentation in synthetic aperture radar

Zheng,

Zhang,

Zhang

2024

Sci Rep

View full text Add to dashboard Cite

A Novel Sea Clutter Suppression Method Based on Deep Learning with Exploiting Time-Frequency Features

Cited by 10 publications

References 9 publications

Marine radar monitoring IoT system and case study of target detection based on PPI images

Marine radar monitoring IoT system and case study of target detection based on PPI images

Artifact Mitigation for High-Resolution Near-Field SAR Images by Means of Conditional Generative Adversarial Networks

Lightweight deep neural network for radio frequency interference detection and segmentation in synthetic aperture radar

Contact Info

Product

Resources

About