Article
Environmental Sciences
Liang Zhang, Zhijun Zhang, Shengtao Lu, Deliang Xiang, Yi Su
Summary: This paper proposes a new superpixel-based non-window CFAR ship detection method for SAR images, which resolves the problems of CFAR detection being affected by speckle noise and having a high computation load caused by the sliding window technique. Experimental results show that the proposed method achieves ship detection with higher speed and accuracy compared to other state-of-the-art methods.
Article
Environmental Sciences
Zhenyu Li, Jianlai Chen, Yi Xiong, Hanwen Yu, Huaigen Zhang, Bing Gao
Summary: A hierarchical scheme of ship detection, imaging, and classification is proposed in this paper, which utilizes a single-channel synthetic aperture radar (SAR) mounted on maneuvering rotor platforms. The scheme involves ship prescreening using an adaptive background window model and discrimination based on micro-Doppler motion properties, which is validated through simulation and field data processing.
Article
Geochemistry & Geophysics
Ming-Dian Li, Xing-Chao Cui, Si-Wei Chen
Summary: Ship monitoring using synthetic aperture radar (SAR) is an important application, with constant false alarm rate (CFAR) methods commonly used for ship detection. However, challenges arise in dense ship detection near shorelines. A new superpixel-level CFAR detector is proposed, incorporating a labeling procedure for discriminating between pure clutter superpixels and mixture superpixels, as well as a nonlocal topology strategy for adaptive threshold estimation. The proposed method outperforms traditional CFAR detectors and recent superpixel methods in detecting inshore dense ship regions.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Hicham Madjidi, Toufik Laroussi
Summary: In this study, an automatic bilateral censoring and detection method is proposed and analyzed for log-normal sea clutter using the AML-CFAR detector. By resorting to linear biparametric adaptive thresholds, a logarithmic amplifier is introduced to transform the distribution to Gaussian. The AML estimates of the unknown mean and standard deviation parameters are used to compute the censoring thresholds and estimate the detection threshold, resulting in better performance compared to state-of-the-art detectors in simulations on both simulated and real SAR images.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Geochemistry & Geophysics
Muhammad Amjad Iqbal, Andrei Anghel, Mihai Datcu
Summary: This letter proposes a novel method for coastline extraction using synthetic aperture radar data, which relies on the Doppler parameter to delineate coastlines in the absence of in-situ data and cloud-free optical images. Results indicate that utilizing scattering from dual and cross-polarization for coastline extraction is more reliable than using co-polarization.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Tao Liu, Ziyuan Yang, Armando Marino, Gui Gao, Jian Yang
Summary: This article presents a novel neighborhood polarimetric covariance matrix (NPCM) technique for detecting small ships in polarimetric synthetic aperture radar (PolSAR) images. By utilizing the spatial correlation between neighborhood pixels, NPCM significantly improves separability between ship targets and sea clutter. However, the use of neighborhood information comes at the expense of higher computation cost.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Hicham Madjidi, Toufik Laroussi, Faical Farah
Summary: Ship detection in SAR images is an important research area. The MAD-CFAR detector proposed in this paper shows good performance in regulating false alarms and detecting ships in a heterogeneous log-normal background.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Geochemistry & Geophysics
Tao Li, Dongliang Peng, Zhikun Chen, Baofeng Guo
Summary: The study introduces a superpixel-level CFAR detector based on truncated Gamma statistics, which improves target detection performance in real SAR images through superpixel segmentation and automatic clutter truncation.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
Tao Liu, Tao Tang, Weijian Liu, Gui Gao
Summary: This study focuses on the polarimetric whitening filter (PWF) used in constant false alarm rate (CFAR) ship detection in polarimetric synthetic aperture radar (PolSAR) imagery. The research aims to obtain an accurate detection threshold by using different statistical models and derives the probability density function, probability of false alarm, and threshold through mathematical methods. Experimental results demonstrate that different statistical models with the same log-cumulants can achieve similar detection performance.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Qianru Wei, Dazheng Feng, Wenjing Jia
Summary: The proposed novel edge detector UDR effectively achieves precise and unbiased detection of SAR image edges through a combination of difference operation and ratio operation, while being insensitive to speckle noise.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Tao Liu, Yanni Jiang, Armando Marino, Gui Gao, Jian Yang
Summary: This study proposes a polarimetric detection optimization filter (PDOF) for ship detection via synthetic aperture radar (SAR). The PDOF is optimized by maximizing the target clutter ratio (TCR), and it has been shown to achieve the best performance in most environments.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Juha Karvonen, Alexandru Gegiuc, Tuomas Niskanen, Anni Montonen, Jorgen Buus-Hinkler, Eero Rinne
Summary: A new unsupervised method for iceberg detection over sea ice-free waters is proposed in this study, which shows a reduced number of false alarms compared to existing algorithms while effectively detecting icebergs. The algorithm is based on the segmentation and nonparametric constant false alarm rate (SnP-CFAR) approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Bengteng Ma, Huizhang Yang, Jian Yang
Summary: In this paper, a ship-detection method for SAR under narrowband RFI environment is proposed. By transforming the input image into frequency domain and suppressing interference data points using adaptively weighting, this method can effectively detect ships.
Article
Environmental Sciences
Peter Lanz, Armando Marino, Thomas Brinkhoff, Frank Koester, Matthias Moeller
Summary: This study examines the performance of several automatic vessel detectors using real SAR data and introduces a new highly performing detector aimed at detecting surface anomalies. Two approaches to combine volume and surface in one algorithm are compared, producing two new detectors. Results are compared using ROC curves, enabling detector comparison independently of threshold selection.
Article
Engineering, Aerospace
Jiaqiu Ai, Zhilin Pei, Baidong Yao, Zhaocheng Wang, Mengdao Xing
Summary: This article proposes an automatic identification system (AIS) data aided Rayleigh constant false alarm rate (AIS-RCFAR) ship detection algorithm of multiple-target environment in synthetic aperture radar (SAR) images. The algorithm effectively eliminates high-intensity outliers in the local background window while accurately modeling the probability density function of the sea clutter. It greatly enhances the detection rate and reduces the false alarm rate.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)
