The Synthetic Aperture Radar (SAR) is unanimously recognized as the most important remote sensing tool for sea oil spill monitoring. The TerraSAR-X satellite can provide highquality, multi-mode X-band SAR-data from Ocean surface for scientific research and associated applications. For the purposes of this study Single Look Slant Range Complex (SSC) Dual Polarization StripMap (SM) TerraSAR-X products are employed. Physically based polarimetric approaches, aimed at exploiting fully the information carried on the scattered waves, have been shown to be useful for both observing oil spills and distinguishing them from biogenic look-alikes [1]-[2]. Following this, the phase difference between the complex HH and VV channels, which has been demonstrated to be suitable to observe sea oil spills in C-band SAR data [2], will be employed to distinguish in physical terms the X-band signal scattered off the slick-free and slick-covered sea surface as images as collected by the new TerraSAR-X satellite. Experiments, accomplished over a meaningful set of SSC dual-polarized TerraSAR-X data in which both oil and look-alikes are present, show that, for both observing sea oil slicks and distinguishing them from weak-damping look-alikes in X-band polarimetric SAR data, the standard deviation of the phase difference is the key information.
Synthetic aperture radar (SAR) is an important instrument for oceanographic observations, providing detailed information of oceans' surface and artificial floating structures. Due to advances in SAR technology and deployment of new SAR satellites, an increasing amount of data is available, and the development of efficient classification systems based on deep learning is possible. A deep neural network has improved the state of the art in classification tasks of optical images, but its use in SAR classification problems has been less exploited. In this paper, a full workflow for SAR maritime targets detection and classification on TerraSAR-X high-resolution image is presented, and convolutional neural networks (CNNs) recently proposed in the literature are cross evaluated on a common data set composed of five maritime classes, namely, cargo, tanker, windmill, platform, and harbor structure. Based on experiments and tests, a multiple input resolution CNN model is proposed and its performance is evaluated. Our results indicate that CNNs are efficient models to perform maritime target classification in SAR images, and the combination of different input resolutions in the CNN model improves its ability to derive features, increasing the overall classification score.
This article describes how a detectability model can be trained in the form of a binary classifier from a data set of synthetic aperture radar (SAR) images of ship wakes, augmented by automatic identification system data. While detectability models for ship signatures exist, ship wake detectability models are only available for simulated data. In order to improve existing ship wake detection algorithms on SAR imagery, there is a need for building a datadriven detectability model which may provide useful a-priori information. A binary L2-regularized logistic regression classifier is trained for each investigated data subset. The dependency on the SAR working frequency is evaluated by analysing a large number of X-and C-band images. In the X-band, the probability of detecting a wake shows dependencies on vessel size and velocity as well as prevailing wind speed. In the C-band, these dependencies are maintained, but with a general reduction in the correlation. This fact led us to the conclusion that, for our data set, ship wakes are more easily imaged in the X-band rather than in the C-band. This is an important outcome, which is supported by a qualitative and quantitative analysis of a large data set of TerraSAR-X and two independent C-band sensors, specifically RADARSAT-2 and Sentinel-1.
The physics of the imaging mechanism underlying the emergence of ship wakes in Synthetic Aperture Radar (SAR) images has been studied in the past by many researchers providing a well-understood theory. Therefore, many publications describe how well ship wakes are detectable on SAR under the influence of different environmental conditions like sea state or local wind, ship properties like ship speed or ship heading, and image acquisition parameters like incidence angle or satellite heading. The increased imaging capabilities of current satellite SAR missions facilitate the collection of large datasets of moving vessels. Such a large dataset of high resolution TerraSAR-X acquisitions now enables the quantitative analysis of the previously formulated theory about the detectability of ship wakes using real data. In this paper we propose an extension of our wake detectability model by using a non-linear basis which allows consideration of all the influencing parameters simultaneously. Such an approach provides new insights and a better understanding of the non-linear influence of parameters on the wake detectability and their interdependencies can now be represented. The results show that the non-linear, interdependent influence of the different influencing parameters on the detectability of wakes matches well to the oceanographic expectations published in the past. Also possible applications of the model for the extraction of missing parameters and automatic for wake detection systems are demonstrated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.