RESUMEBien que Ie potentiel de detection des icebergs ait augmente considerablement au cours des dernieres decennies, la surveillance et la detection des icebergs presentent des limitations qui representent toujours un obstacle a la securite et a I 'efficacite des operations maritimes. Le transport maritime transatlantique est soumis a des detours significatifs vers Ie sud durant la saison des glaces et les installations et les procedures de production petroliere au large doivent eire concues specifiquement pour operation dans les eaux ou les icebergs sont presents incluant Ie recours ades navires additionnels dedies ala "gestion des icebergs ". Ainsi, des efforts considerables sont orientes vers Ie developpement d 'outils de teledetection pour la detection plus flable et dans toutes les conditions meteorologiques des icebergs. Le radar asynthese d'ouverture (RSO) de RADARSAT-I permet d 'accroitre de facon substantielle la frequence et la precision de la detection des icebergs. Cet article presente des resultats obtenus dans Ie cadre de I 'etude de validation pour determiner Ie potentiel de RADARSAT-I dans la detection des icebergs realisee au cours de I 'annee 2000 sur la cote est du Canada. Des images en mode faisceau large 2 et 3 et ScanSAR en mode B etroit ont ete acquises adifferents endroits pres des cotes et au large de Terre-Neuve durant les mois de mai et juin. Des donnees de realite de terrain relatives aux icebergs, basees principalement sur I 'utilisation de la photographie aerienne aechelle, ont ete acquises parallelement aux acquisitions RADARSAT-I. Les positions des icebergs derivees de la realite de terrain ont ete correlees avec les localisations de cibles dans les images RADARSAT-I et les caracteristiques des signatures des icebergs aI'interieur des images RSO ont ete documentees. Des techniques de taux de fausses alarmes constant (TFAC) ont ete utilisees pour determiner de facon empirique la probabilite de detection des icebergs en tant que fonction de la dimension de I 'iceberg, de la vitesse du vent et de I 'angle d'incidence du radar. Pour les angles RSO plus grands que 35 degres, on peut generalement detecter les icebergs d 'une dimension de I'ordre de la resolution du mode RSO utilise. Quant aux icebergs plus grands, il est possible de les detecter de facon plus constante et meme dans des conditions de mer agitee.
SUMMARYThough iceberg detection capability has increased considerably over the past several decades, surveillance and detection limitations still present an obstacle to the safety and ejJiciency of marine operations. Transatlantic shipping incurs significant southerly detours during the ice season and offihore oil production facilities and procedures must be specially designed for operation in icebergfrequented waters, including additional ships dedicated to iceberg "management". As a result, considerable effort has been expended in the development of various remote sensing toolsfor reliable, all-weather detection oficebergs. The RADARSAT-l synthetic aperture radar (SAR) satellit...
Spaceborne synthetic aperture radar (SAR), with its wide area coverage and all-weather operation, is an ideal sensor to provide iceberg surveillance in support of safe shipping and offshore operations. Reliable ship/iceberg discrimination in SAR imagery is at least as important as detection since misclassification can result in expending significant resources for investigation or avoidance. To address this need, the authors have undertaken research to facilitate effective target discrimination using SAR multi-polarization data. The results presented here are for iceberg and ship classification for ENVISAT advanced synthetic aperture radar (ASAR) HH/HV data. Target classification was achieved by maximizing the a posteriori probabilities obtained from Bayes's rule.The maximum likelihood Gaussian classifier was used to model the probability of an unknown target belonging to either the iceberg or ship class. The feature selection algorithms, sequential forward selection (SFS), genetic algorithm (GA), and exhaustive search (ES) were evaluated for optimization of a feature space dependant multivariate classifier. The results from this study show for dual polarized HH/HV ASAR, icebergs and ships can be classified with a 93.5% accuracy using a two-class maximum likelihood model. As well, for the small sample set of 201 iceberg and ship targets presented here, suboptimal feature selection algorithms such as the SFS, GA, and exhaustive ranked search (ERS) are considered. These feature selection methods were considerably less computationally expensive to run than the global exhaustive search and were found to have converging results for both accuracy and features selected.
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.