Search

This paper analyzes the potentialities to classify vessels detected through optical and synthetic-aperture radar (SAR) satellite-borne platforms and estimate their motion. For classification, the discriminative power of a set of geometric features extracted from segmented remote-sensed images is evaluated by clustering data derived from a set of accurate footprints belonging to either tanker or cargo ships. The same procedure is repeated on a few dozens of real, remote-sensed optical images. Concerning velocity estimation, which in this context is based on the detection and analysis of the wake pattern generated by the ship motion, a discussion concerning the accuracy of the wake detection task is presented. In particular, since wake patterns are usually hard to detect, a method is proposed to enhance the wake signal-to-noise ratio, based on a dedicated pre-filtering stage. Results returned by the proposed method are compared with those obtained adopting a standard literature approach, eventually observing that the introduction of the pre-filtering stage improves the wake detection accuracy. A maritime surveillance system based on a pipeline of the modules described here represents a useful tool to support the authorities in charge of monitoring maritime traffic with safety, security and law enforcement purposes.

The main purpose of this paper is to describe a software platform dedicated to sea surveillance, capable of detecting and identifying illegal maritime traffic. This platform results from the cascade pipeline of several image processing algorithms that input Radar or Optical imagery captured by satellite-borne sensors and try to identify vessel targets in the scene and provide quantitative descriptors about their shape and motion. This platform is innovative since it integrates in its architecture heterogeneous data and data processing solutions with the goal of identifying navigating vessels in a unique and completely automatic processing streamline. More in detail, the processing chain consists of: (i) the detection of target vessels in an input map, (ii) the estimation of each vessel&rsquo, s most descriptive geometrical and scatterometric (for radar images) features, (iii) the estimation of the kinematics of each vessel, (iv) the prediction of each vessel&rsquo, s forthcoming route, and (v) the visualization of the results in a dedicated webGIS interface. The resulting platform represents a novel tool to counteract unauthorized fishing and tackle irregular migration and the related smuggling activities.

Tècniques de detecció de moviment amb radars d'apertura sintètica multicanals sobre escenaris marítims. [ANGLÈS] Multichannel spaceborne and airborne synthetic aperture radars (SAR) offer the opportunity to monitor maritime traffic through specially designed instruments and applying a suitable signal processing in order to reject sea surface clutter. These processing techniques are known as Moving Target Indication techniques (MTI) and the choice of the most adequate method depends on the radar system and operating environment. In maritime scenes the seas presents a complicated clutter whose temporal/spatial coherence models and background reflectivity depends on a large number of factors and are still subject of research. Moreover the targets kinematics are influenced by the sea conditions, producing in some situations high alterations in the imaged target. These aspects make difficult the detectability analysis of vessels in maritime scenarios, requiring both theoretical models and numerical simulations. This thesis looks into the few available MTI techniques and deals experimentally with them in a developed simulator for maritime SAR images. The results are also presented in a image format, giving the sequence for one trial simulation and the asymptotic probability of detection for the simulated conditions. [CASTELLÀ] Los radares de apertura sintética (SAR) multicanal a bordo de satélites o plataformas aerotransportadas ofrecen la oportunidad de monitorizar el tráfico marítimo a través de instrumentos especialmente diseñados y procesando los datos recibidos de forma adecuada para rechazar la señal provocada por la reflexión del mar. A estas técnicas se las conoce como Moving Target Indication techniques (MTI) y la elección de la más adecuada depende del sistema y del entorno de aplicación. En escenarios marinos, el mar presenta un clutter complicado de modelar, cuya coherencia espacio-temporal y reflectividad radar dependen de un gran número de factores que hoy en día todavía siguen siendo investigados. Por otra parte los parámetros dinámicos del target estan influenciados por las condiciones del mar, produciendo en algunas situaciones graves alteraciones en la formación de la imagen. Estos aspectos dificultan el análisis de la detección de las embarcaciones, requiriendo modelos teóricos y simulaciones numéricas. Este Proyecto Final de Carrera investiga las técnicas MTI disponibles, aplicándolas sobre las imágenes marítimas generadas por un simulador SAR. Los resultados son la generación de los productos MTI en formato imagen y el cálculo de la probabilidad de detección para cada target. [CATALÀ] Els radars d'obertura sintètica (SAR) multicanal embarcats en satèl·lits o plataformes aerotransportades ofereixen l'oportunitat de monitoritzar el tràfic marítim a través d'instruments especialment dissenyats i processant les dades rebudes de forma adequada per rebutjar la senyal provocada per la reflexió del mar. A aquestes tècniques se les coneix com Moving Target indication techniques (MTI) i l'elecció de la més adequada depèn del sistema i de l'entorn d'aplicació. En escenaris marins, el mar presenta un clutter complicat de modelar, la coherència espai-temporal i reflectivitat radar depenen d'un gran nombre de factors que avui dia encara segueixen sent investigats. D'altra banda els paràmetres dinàmics del target estan influenciats per les condicions de la mar, produint en algunes situacions greus alteracions en la formació de la imatge. Aquests aspectes dificulten l'anàlisi de la detecció de les embarcacions, requerint models teòrics i simulacions numèriques. Aquest Projecte Final de Carrera investiga les tècniques MTI disponibles, aplicant-les sobre les imatges marítimes generades per un simulador SAR. Els resultats són la generació dels productes MTI en format imatge i el càlcul de la probabilitat asimptòtica de detecció per a cada target.