Ship detection using X-band dual-pol SAR data

Angelliaume, Sébastien; Durand, P.; Souyris, J.-C.

doi:10.1109/igarss.2011.6050065

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This "multi-faceted" surveillance [22] involves a wide range of systems : on-board transmission devices (Automatic Identification System -AIS [27]; Vessel Monitoring System -VMS [28]), recording systems (Voyage data recorder [29]), marine radars (frequencies ranging from HF to X-band [30][31][32]) or imagery (in situ observation, aircraft, drone, satellite [33]), each with its specific characteristics in terms of spatial and temporal coverage and resolution, existence and precision of associated metadata, format, fleet coverage.…”

Section: Setting the Scene With Maritime Surveillance Data?mentioning

confidence: 99%

Exploring uses of maritime surveillance data for marine spatial planning: A review of scientific literature

et al. 2020

View full text Add to dashboard Cite

Maritime Spatial Planning (MSP) has become of key interest in many countries around the world in the last decade, leading to an increased need to inform the historical spatial and temporal footprint of maritime activities. If this knowledge was still recently considered a blind spot, recent developments of maritime surveillance systems (e.g. AIS, VTS, VMS) have allowed to fill some of these gaps by generating significant amounts of spatial data on ships at sea. In this paper, the use of these maritime surveillance data for planning purposes is explored through the lens of the international scientific literature. A first set of 2030 articles dealing with maritime surveillance data and collected through the Web of Science collection was explored to determine the type of data used, the maritime activities addressed and the main objective of each paper (technical developments, safety and security, environmental protection, MSP). This allowed to highlight the growing interest on maritime surveillance data in the scientific literature over the past decades, predominantly towards AIS data and shipping. Over the 2030 papers, only 63 dealt specifically with MSP. These were extracted and explored, allowing to highlight the potential of these data to feed in MSP processes, with a specific focus on fisheries. Nevertheless, the description of actual uses of surveillance-based information within MSP processes remained particularly rare. If this can be seen as a result of a science-policy delay, we suggest that it is mostly related to issues of accessibility, acceptance by economic stakeholders and appropriation by decision makers.

show abstract

Section: Setting the Scene With Maritime Surveillance Data?mentioning

confidence: 99%

Exploring uses of maritime surveillance data for marine spatial planning: A review of scientific literature

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Their results show that the polarization entropy of ship and sea clutter has good contrast, whereas the incidence angle is smaller than 60 • . Along with the development of SAR imaging technology and the analysis of the electromagnetic scattering mechanism, the eigenvalue decomposition method based on the polarimetric coherency matrix has been widely used to detect ships in PolSAR imagery (Angélliaume, Durand, and Souyris 2011;Arii, Xyl, and Kim 2011;Chen, Chen, and Yang 2009;Marino and Walker 2011).…”

Section: Feature Selection and Weighted Svm Classifier-based Ship Detmentioning

confidence: 99%

Feature selection and weighted SVM classifier-based ship detection in PolSAR imagery

Xing

Zou

et al. 2013

International Journal of Remote Sensing

View full text Add to dashboard Cite

Target decomposition is an important method for ship detection in polarimetric synthetic aperture radar (SAR) imagery. Parameters such as the polarization entropy and alpha angle deduced from the coherency matrix eigenvalue decomposition capture the differences between the target and background from different views separately. However, under the conditions of a relatively high resolution and a rough sea, the contrast between ship and sea reduces in the aforementioned space. Based on the analyses of target decomposition theory and the target's scattering mechanism, multi-polarization parameters can be used to characterize different scattering behaviours of the ship target and sea clutter. Moreover, each parameter has its own diverse significance in the practical detection problem. This article proposes a feature selection and weighted support vector machine (FSWSVM) classifier-based algorithm to detect ships in polarimetric SAR (PolSAR) imagery. First, the method constructs a feature vector that consists of multi-polarization parameters. Then, different polarization parameters are refined and weighted according to their significance in the support vector machine (SVM) classifier. Finally, ships are classified from the sea background and other false alarms by the classifier. The validation results on National Aeronautics and Space Administration/Jet Propulsion Laboratory (NASA/JPL) airborne synthetic aperture radar (AIRSAR) and Radarsat-2 quad polarimetric data illustrate that the method detects ship targets more precisely and reduces false alarms effectively.

show abstract