Saliency detection of targets in polarimetric SAR images based on globally weighted perturbation filters

Monitoring riverine traffic from space: The untapped potential of remote sensing for measuring human footprint on inland waterways

“…Approaches utilising Synthetic Aperture Radar (SAR) imagery, which are not affected by cloud cover, could potentially supplement the analysis by filling these temporal data gaps. SAR has long been utilised for marine surveillance with a range of traditional feature-based (Eldhuset, 1996;Iervolino and Guida, 2017;Yang et al, 2019) and deep learning (Jin et al, 2020;Zhang et al, 2021;Zhang et al, 2020) approaches developed over the years. However, only limited attention has been given to riverine settings, with a focus on the detection of large vessel clusters (≥70 m in length) with Sentinel-1 imagery (Gruel et al, 2022;Gruel and Latrubesse, 2021).…”

PolSAR Target Detection via Reflection Symmetry and a Wishart Classifier

“…Marino [7] proposed a series of detection methods for ship detection in polarimetric SAR images, including the geometrical perturbation polarimetric notch filter (GP-PNF) for the problem of partial-target detection. Then, Yang et al [19] proposed a saliency detector for PolSAR images based on weighted perturbation filters; Gao et al [20] [21] proposed a CFAR ship detector in nonhomogeneous sea clutter in PolSAR data based on the notch filter and proposed a ship detector in compact PolSAR data base on the notch filter. Wang et al [8] proposed a new PolSAR ship detector based on superpixel-level scattering mechanism distribution features to improve the target detection performance under a low target-to-clutter ratio.…”

An Improved SAR Ship Classification Method Using Text-to-Image Generation-Based Data Augmentation and Squeeze and Excitation

“…Since the launch of the first SAR ocean remote sensing satellite, SEASAT, by the United States back in 1978 [3], research in the field of sea surface ship monitoring has been continuously thriving. Over the years, there have been numerous mathematical approaches used in this field, such as those based on the generalized likelihood ratio [4], polarization decomposition [5], and visual saliency [6]. While these classical algorithms have achieved good detection and performance recognition results in certain marine application scenarios, they rely on establishing mathematical models and manual feature extraction based on the operator's experience.…”