This paper presents a Ship Monitoring System (SIMONS) working with Synthetic Aperture Radar (SAR) images. It is able to infer ship detection and classification information, and merge the results with other input channels, such as polls from the Automatic Identification System (AIS). Two main stages can be identified, namely: SAR processing and data dissemination. The former has three independent modules, which are related to Coastline Detection (CD), Ship Detection (SD) and Ship Classification (SC). The later is solved via an advanced web interface, which is compliant with the OpenSource standards fixed by the Open Geospatial Consortium (OGC). SIMONS has been designed to be a modular, unsupervised and reliable system that meets Near-Real Time (NRT) delivery requirements. From data ingestion to product delivery, the processing chain is fully automatic accepting ERS and ENVISAT formats. SIMONS has been developed by GMV Aerospace, S.A. with three main goals, namely: 1) To limit the dependence on the ancillary information provided by systems such as AIS. 2) To achieve the maximum level of automatism and restrict human manipulation. 3) To limit the error sources and their propagation. Spanish authorities have validated SIMONS. The results have been satisfactory and have confirmed that the system is useful for improving decision making. For single-polarimetric images with a resolution of 30 m, SIMONS permits the location of ships larger than 40 m with a classification ratio around 50% of positive matches. These values are expected to be improved with SAR data from new sensors. In the paper, the performance of SD and SC modules is assessed by cross-check of SAR data with AIS reports.
[1]
Kazuo Tanaka,et al.
An Introduction to Fuzzy Logic for Practical Applications
,
1996
.
[2]
D. Wehner.
High Resolution Radar
,
1987
.
[3]
Ian G. Cumming,et al.
Digital Processing of Synthetic Aperture Radar Data: Algorithms and Implementation
,
2005
.
[4]
Tony F. Chan,et al.
Active contours without edges
,
2001,
IEEE Trans. Image Process..
[5]
Carlos López-Martínez,et al.
A novel algorithm for ship detection in SAR imagery based on the wavelet transform
,
2005,
IEEE Geoscience and Remote Sensing Letters.
[6]
Jordi J. Mallorqui,et al.
Scattering-Based Model of the SAR Signatures of Complex Targets for Classification Applications
,
2008
.
[7]
Carlos López-Martínez,et al.
Automatic Detection of Spots and Extraction of Frontiers in SAR Images by Means of the Wavelet Transform: Application to Ship and Coastline Detection
,
2006,
2006 IEEE International Symposium on Geoscience and Remote Sensing.
[8]
Jordi J. Mallorquí,et al.
Single-Pass Polarimetric SAR Interferometry for Vessel Classification
,
2007,
IEEE Transactions on Geoscience and Remote Sensing.