Conference Paper

Validation of a CFAR vessel detection algorithm using known vessel locations

Authors:
If you want to read the PDF, try requesting it from the authors.

Abstract

The National Oeanic and Atmospheric Administration (NOAA)/National Environmental Satellite, Data, And Information Service (NESDIS) is in the second year of a two-year demonstration of Synthetic Aperture Radar (SAR) derived products called the Alaska SAR Demonstration (AKDEMO). This demonstration provides near real-time SAR data and derived products, including wind images and vectors, hard target locations, along with ancillary data, to specific users in the government community. One of the derived products are vessel positions obtained from a constant false alarm rate (CFAR) vessel detection algorithm developed by Veridian ERIM. This algorithm has been tested and validated to maximize the number of ships found while minimizing the number or false alarms on one SAR image of the Red King Crab fishery in Bristol Bay on October 18, 1999. This resulted in using a detection statistic threshold of about 5.5, depending on image resolution used. Until now, this validation has been done with only general knowledge of fishing fleet size and location, but no in situ vessel information. This paper presents the results of a validation of the SAR vessel detection algorithm using observer reported vessel positions along with information on vessel size and local wind speed

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... The proposed algorithm only requires the intensity of HV and HH polarization channels; therefore, the polarimetric capability is not fully exploited here. The window sizes used are w test = [21,21] and w train = [101, 101] pixels. These window sizes are selected in order to have a test window that is in between 100 and 200 m of size, and it is comparable with the following tests performed with Sentinel-1 data. ...
... The proposed algorithm only requires the intensity of HV and HH polarization channels; therefore, the polarimetric capability is not fully exploited here. The window sizes used are w test = [21,21] and w train = [101, 101] pixels. These window sizes are selected in order to have a test window that is in between 100 and 200 m of size, and it is comparable with the following tests performed with Sentinel-1 data. ...
Article
Icebergs represent hazards to maritime traffic and offshore operations. Satellite synthetic aperture radar (SAR) is very valuable for the observation of polar regions, and extensive work was already carried out on detection and tracking of large icebergs. However, the identification of small icebergs is still challenging especially when these are embedded in sea ice. In this paper, a new detector is proposed based on incoherent dual-polarization SAR images. The algorithm considers the limited extension of small icebergs, which are supposed to have a stronger cross-polarization and higher cross- over copolarization ratio compared to the surrounding sea or sea ice background. The new detector is tested with two satellite systems. First, RADARSAT-2 quad-polarimetric images are analyzed to evaluate the effects of high-resolution data. Subsequently, a more exhaustive analysis is carried out using dual-polarization ground-detected Sentinel-1a extra wide swath images acquired over the time span of two months. The test areas are in the east coast of Greenland, where several icebergs have been observed. A quantitative analysis and a comparison with a detector using only the cross-polarization channel are carried out, exploiting grounded icebergs as test targets. The proposed methodology improves the contrast between icebergs and sea ice clutter by up to 75 times. This returns an improved probability of detection.
... Typically, the detection of ship pixels is based [10]- [13] on the selection of pixels with brightness above a threshold value, which can be the same for the entire image, leading to "global threshold algorithms" or can vary through the image, leading to the "adaptive threshold algorithms", which are more commonly used. ...
... Finally, the background window should be large enough to generate good estimates of the background statistics but it should not include neighboring bright targets. Literature suggests [12]- [13] background window sizes equal to 2.5-3 times the largest ship dimension. ...
Conference Paper
The paper focuses on similarities and difference between adaptive threshold and sub-look processing in ship detection by Synthetic Aperture Radar (SAR). The main goal is to formalize the cascade application of both methods to achieve an overall reduction of the false alarm rate. The methods are tested on TerraSAR-X stripmap SAR data collected over the Gulf of Naples, Italy. Input parameters are set considering vessel traffic statistics in the area. Preliminary results confirm the capability of both the methods to attain very high detection rate (with zero missed detections in the considered case), and show that the synergic use of the methods reduces the number of false alarms, with respect to application of a single method.
... Some studies used these data to assess the impact of Covid-19 on marine traffic (March et al., 2021). Alternatively, the development of Synthetic Aperture Radar (SAR) satellites has unlocked the possibility of detecting the location of marine vessels without requiring voluntary or automatic reporting via transmitters on board (Friedman et al., 2001;Pelich et al., 2015;Stasolla et al., 2016). Using an active sensor system, SAR images can be taken by day or night and regardless of weather conditions (Fernandez Arguedas et al., 2016). ...
Article
Full-text available
The Covid-19 pandemic is the latest example in a growing number of health, social, economic, and environmental crises humanity is facing. The multiple consequences of this pandemic crisis required strong responses from governments, including strict lockdowns. Yet, the impact of lockdowns on coastal ecosystems and maritime activities is still challenging to quantify over large spatial scales in comparison to the pre-Covid period. In this study, we used an object detection algorithm on Synthetic Aperture Radar (SAR) images acquired by the two Sentinel-1 satellites to assess the impact of the Covid-19 crisis on the presence of boats before, during and after lockdown periods in the French Mediterranean Exclusive Economic Zone. During the French most severe lockdown period (March – May 2020), we observed that ship frequentation remained at the same level from March to July 2020, instead of rising towards the summer peak like in previous years. Then, ship frequentation increased rapidly to a normal level in August 2020 when restrictions were lifted. By comparing morning and evening (7:00 am and 7:00 pm) ship frequentation during this period to pre-Covid years, we observed contrasting patterns. On the one hand, morning detections were particularly high, while on the other hand evening detections were significantly lower and less concentrated in coastal touristic waters than in previous years. Overall, we found a 9% decrease in ship frequentation between the year 2020 and the 2017-2019 period, with a maximum of 43% drop in June 2020 due to the lockdown. So, the Covid -19 crisis induced only a very short-term reduction in maritime activities but did not markedly reduce the annual ship frequentation in the French Mediterranean waters. The satellite imagery approach is an alternative method that improves our understanding of the pandemic impacts at an unprecedented spatiotemporal scale and resolution.
... The effect of ship orientation on ship detectability has been pointed out by Vachon et al. (1997) andFriedman et al. (2001). Margarit and his colleagues have integrated detailed ship and sea surface scattering models with a SAR simulation system (called GRECOSAR) that can model polarimetric backscatter as a function of the dynamic three-dimensional ship orientation (Margarit & Tabasco, 2011). ...
Article
Full-text available
The RADARSAT Constellation Mission (RCM) planned to be launched in 2018 is designed to support maritime surveillance requirements in which ice, wind, oil pollution, and ships are to be monitored by providing wide swath beam modes. In this article, we introduce the first analysis of ship detection performance using simulated RCM data. We report ship detection performance using a likelihood ratio test (LRT) for three wide swath RCM imaging modes: Ship Detection (25 m), Low Resolution (100 m), and Medium Resolution (50 m). These beam modes were assessed for a number of dual-polarimetric (dual-pol) systems, including the standard linear polarizations as well as compact polarimetry (CP). These data were simulated from RADARSAT-2 Fine Quad (FQ) mode in the three RCM modes. Furthermore, the detection performance of the pseudo-quad data reconstructed from the simulated circular transmit, linear receive data is also investigated and compared to the other systems’ performance for the three RCM modes. The receiver operating characteristic curves are used in this study as the basic measure of detection performance for all beam modes and all detectors. We found that the compact polarimetric SAR detectors outperform the conventional linear dual-pol detectors at the three RCM modes for ship detection for medium to high incidence angles. At steep angles, the performance of the two polarization configurations was comparable. Our study confirmed that detection performance improved as incidence angle and spatial resolution increased. We also investigated the impact of the ship orientation with respect to the radar beam and found that detection performance was generally higher when ship was oriented perpendicular to the radar beam.
... Starting in 2003, mapped vessel positions will be internally produced in ARCGIS shape file format. Past work has been done to find the appropriate threshold for vessel detection using the Veridian Systems Division CFAR algorithm [2][4][5]. The results from these studies used either general fleet descriptions and/or in situ data from Alaska Department of Fish & Game (ADF&G) observer vessels participating in the Bristol Bay Red King Crab Fishery. ...
Conference Paper
The National Oceanic and Atmospheric Administration (NOAA) National Environment Satellite, Data, and Information Service (NESDIS) provides synthetic aperture radar (SAR) derived products under a demonstration project named the Alaska SAR Demonstration (AKDEMO) to the US government community. The AKDEMO near real-time data and products include SAR wind images and vectors, hard target locations, and ancillary data. The hard target locations are available for use in fishery management by agencies such as the Alaska Department of Fish and Games (ADF&G), the National Marine Fisheries Service ( NMFS) and the United States Coast Guard (USCG). Vessel positions are obtained form hard target signatures through the use of a constant false alarm rate (CFAR) vessel detection algorithm developed by Veridian Systems Division. This algorithm has gone through testing and validation, using fleet information and vessel observer reports, during the Red King Crab fisheries in Alaska in 1999 and 2000. The goal was to maximize the number of ships found while minimizing the number or false alarms. Using general fleet location information, it was found that the minimum vessel size detected by the CFAR algorithm was 36 m using RADARSAT-1 ScanSAR wide mode data with a nominal spatial resolution of 100 m. Still, when comparing the CFAR results with the actual positions reported by the ship observers, vessels over 36 m were not always detected. This led to the hypothesis that the heading and perhaps wind conditions may have affected the ability of the SAR to detect the vessels. In 2001, vessel observers again reported their positions during SAR overpasses, this time also reporting heading and wind conditions. Unfortunately, due to high winds and waves, SAR was not able to detect the fishing fleet. In 2002, this was repeated, resulting in 3 days during the fishery opening when RADARSAT-1 was able to image the fishing fleet in the ScanSAR wide B mode. Approximately twenty ships each day in the a rea covered by the RADARSAT-1 data reported their position and heading. Results showing the dependence between RADARSAT-1 vessel detection and vessel heading are presented using the GIS platform.
... The effect of ship orientation on ship detectability has been pointed out by Vachon [4] and Friedman [44]. Margarit and his colleagues have integrated detailed ship and sea surface scattering models with a SAR simulation system (called GRECOSAR) that can model polarimetric backscatter as a function of the dynamic three-dimensional ship orientation [45], [46]. ...
Article
Quad-pol data are generally acknowledged as providing the highest performance in ship detection applications using SAR data. Yet quad-pol data have half the swath width of single and dual-pol data and are thus less useful for maritime surveillance, where wide area coverage is crucial. Compact polarimetry (CP) has been proposed as a compromise between swath width and polarization information. The circular-transmit-linear-receive (CTLR) CP data have certain engineering advantages over other CP configurations. CP data may be used to reconstruct a reduced quad-pol covariance matrix (termed pseudo-quad, or PQ, data) and the potential of these data in terrestrial applications has recently been demonstrated. We present some of the first results on the use of CTLR data and reconstructed quad-pol data for ship detection. We use Radarsat-2 fine-quad (FQ) data to examine 76 ships over a range of incidence angles and ship orientations at low to moderate wind speeds. We examined the ship detection performance of full quad-pol and full-PQ data; several dual-pol configurations suggested in the literature, HV and PQ HV and the raw CTLR data. We find that the ship detection performance of the PQ HV data is the strongest of all the detectors we examined, with performance that was comparable to quad-pol data. Other strong performers were HV and CTLR data.
... For this reason, ships often appear as bright spots in SAR intensity images. This peculiarity has led to the development of several algorithms aimed at detecting bright points on a darker background [3,[15][16][17][18][19][22][23][24][25][26][27][28][29][30]. The backscattering from the sea is strongly influenced by the sea state, and in some situations, it can be extraordinarily bright, covering the return from small vessels. ...
Article
Full-text available
The surveillance of maritime areas with remote sensing is vital for security reasons, as well as for the protection of the environment. Satellite-borne synthetic aperture radar (SAR) offers large-scale surveillance, which is not reliant on solar illumination and is rather independent of weather conditions. The main feature of vessels in SAR images is a higher backscattering compared to the sea background. This peculiarity has led to the development of several ship detectors focused on identifying anomalies in the intensity of SAR images. More recently, different approaches relying on the information kept in the spectrum of a single-look complex (SLC) SAR image were proposed. This paper is focused on two main issues. Firstly, two recently developed sub-look detectors are applied for the first time to ship detection. Secondly, new and well-known ship detection algorithms are compared in order to understand which has the best performance under certain circumstances and if the sub-look analysis improves ship detection. The comparison is done on real SAR data exploiting diversity in frequency and polarization. Specifically, the employed data consist of six RADARSAT-2 fine quad-polacquisitions over the North Sea, five TerraSAR-X HH/VV dual-polarimetric data-takes, also over the North Sea, and one ALOS-PALSAR quad-polarimetric dataset over Tokyo Bay. Simultaneously to the SAR images, validation data were collected, which include the automatic identification system (AIS) position of ships and wind speeds. The results of the analysis show that the performance of the different sub-look algorithms considered here is strongly dependent on polarization, frequency and resolution. Interestingly, these sub-look detectors are able to outperform the classical SAR intensity detector when the sea state is particularly high, leading to a strong clutter contribution. It was also observed that there are situations where the performance improvement thanks to the sub-look analysis is not so noticeable.
... Ship detection on SAR images has been intensively studied using data acquired from the Canadian Radarsat-1 satellite and the European satellites: ERS-1/2 (European Remote Sensing) and ENVISAT (Environmental Satellite). The detection capabilities from the aforementioned C-band data have been studied in [2], [3], [4]. More recent spaceborne SAR sensors, namely the Canadian Radarsat-2 (RS-2) satellite, the Italian CosmoSkyMed (CSK) satellites constellation or the German TerraSAR-X satellite, may provide additional capabilities for ship detection. ...
Article
This paper studies the performances of different ship detectors based on adaptive threshold algorithms. The detection algorithms are based on various clutter distributions and assessed automatically with a systematic methodology. Evaluation using large datasets of medium resolution SAR images and AIS (automatic identification system) data as ground truths allows to evaluate the efficiency of each detector. Depending on the datasets used for testing, the detection algorithms offer different advantages and disadvantages. The systematic method used in discriminating real detected targets and false alarms in order to determine the detection rate, allows us to perform an appropriate and consistent comparison of the detectors. The impact of SAR sensors characteristics (incidence angle, polarization, frequency and spatial resolution) is fully assessed, the vessels’ length being also considered. Experiments are conducted on Radarsat-2 and CosmoSkymed ScanSAR datasets and AIS data acquired by coastal stations.
... The first products were images of SAR-derived wind speed developed by The Johns Hopkins University Applied Physics Laboratory [2,3]. Complete product production was in place by March 2000 when SAR imagery, vessel detection and wind vector products (with directions obtained from wind-aligned features in the SAR image itself) developed by Veridian Systems Division were implemented [4,5]. Also implemented at this time was a web-based product viewing and analysis system called the WWW Information Processing Environment (WIPE) developed by Applied Coherent Technologies (ACT) Inc. [6]. ...
Conference Paper
A summary of the interim results of the first two years of the authors' NASA RADARSAT-1 ADRO-2 SAR project is given. The Alaska SAR Demonstration (AKDEMO) is providing winds, vessel positions, and SAR imagery to users in Alaska for evaluation as to their utility to operational government agencies responsible for ocean and weather prediction and fisheries management/enforcement. The AKDEMO applications are maturing and their accuracy has been measured. A new demonstration, the Gulf of Mexico Experiment (GoMEx), is now underway to examine use of SAR data and products in hazardous algal bloom (HAB) and oil spill/seep monitoring. Initial results show correspondence of bloom signatures in ocean color and SAR data in areas of high HAB concentration as measured from ship water samples. In addition to these two applications demonstrations, research is underway in the use of SAR data to study upwelling, river plumes, ocean current boundaries, atmospheric boundary layer processes, and other applications. This research will continue into the third and final year of the ADRO-2 project.
... Among the non-recurrent detections, 34% of them remain uncorrelated, while 66% are correlated to interpolated reported positions. Table 3 also shows the total number of the sources of recurrence (12,300), as well as the sources categorised as fixed structures (9565) and as ambiguities (2735). These numbers give an estimate of how many locations with fixed structures outside the OpenStreetMap used in SUMO and with ambiguities from strong land-based scatterers (not already flagged by SUMO) exist in the Med and can be detected in Sentinel-1 images. ...
Article
Full-text available
The free, full and open data policy of the EU's Copernicus programme has vastly increased the amount of remotely sensed data available to both operational and research activities. However, this huge amount of data calls for new ways of accessing and processing such "big data". This paper focuses on the use of Copernicus's Sentinel-1 radar satellite for maritime surveillance. It presents a study in which ship positions have been automatically extracted from more than 11,500 Sentinel-1A images collected over the Mediterranean Sea, and compared with ship position reports from the Automatic Identification System (AIS). These images account for almost all the Sentinel-1A acquisitions taken over the area during the two-year period from the start of the operational phase in October 2014 until September 2016. A number of tools and platforms developed at the European Commission's Joint Research Centre (JRC) that have been used in the study are described in the paper. They are: (1) Search for Unidentified Maritime Objects (SUMO), a tool for ship detection in Synthetic Aperture Radar (SAR) images; (2) the JRC Earth Observation Data and Processing Platform (JEODPP), a platform for efficient storage and processing of large amounts of satellite images; and (3) Blue Hub, a maritime surveillance GIS and data fusion platform. The paper presents the methodology and results of the study, giving insights into the new maritime surveillance knowledge that can be gained by analysing such a large dataset, and the lessons learnt in terms of handling and processing the big dataset.
... procedure should be performed prior to the estimation of the wind speed. This study used the adaptive threshold method to detect ship pixels in the SAR images based on the peculiar scattering characteristics ( Friedman et al. 2001;Chen et al. 2005;Martín-de- Nicolás et al. 2015). The adaptive threshold method is one of the most widely used methods for target detection in the SAR images, since neither high computational efficiency nor additional data information are necessary for its execution. ...
Article
Full-text available
Environmental factors affecting the errors in wind speed estimates were investigated using the Advanced Land Observing Satellite-2 Phased Array L-band Synthetic Aperture Radar-2 (ALOS-2 PALSAR-2) data for the period from 1 November 2014 to 30 November 2017. In total, 45 ALOS-2 PALSAR-2 Stripmap Fine mode images with horizontal dual-polarization were collected, and the wind speeds were calculated using the L-band Geophysical Model Function (GMF) in 2009. Validation of the SAR-derived wind speeds to in-situ wind, converted to the 10-m neutral wind, resulted in the root-mean-square error of 2.11 ms⁻¹, bias error of −1.16 m s⁻¹, and standard deviation of 1.78 m s⁻¹. Investigation of the wind speed errors revealed the contributions of diverse oceanic environmental factors such as the ship and its side-lobe effect that is negligible at a distance of more than 200% of the ship radius, v-shaped ship wakes are accompanied by the Kelvin waves and turbulent wakes caused by ship movement. The sand ridge, formed due to the interaction of shallow bathymetry and tidal currents, contributed to the wind speed errors of more than 50%. The internal waves caused prominent wind speed errors of more than 100%. The atmospheric gravity waves, generated by the orographic effect, caused wind speed fluctuations up to 13.4 m s⁻¹. This study addressed the importance of understanding the factors that affect the normalized radar cross-section of the SAR image in order to correctly retrieve wind speeds from SAR data.
Article
The paper considers the problem of using images from SAR satellites for the identification of seagoing vessels. It describes the main functions of software and technological complex of the automated monitoring. The system is operated with utilizing space images of SAR satellites Sentinel 1A (B). The algorithmic part, which implements the detection on the sea surface the marks associated with ships, is described in details. To reduce the impact of speckle-noise, the image is pre-processed with the improved Lee-filter. Further processing lies in using an adaptive threshold algorithm that provides detection for each local background fragment of the image the unusually bright pixels, at the same time the algorithm provides a constant probability of error. By solving a nonlinear equation, for each position of the background window the algorithm finds the threshold brightness value and then all pixels above this value are considered vessels. In advance the evaluation of parameters of statistical distribution of pixels’ brightness is performed for each position of the background window. K-mean is used for such distribution. The selected bright pixels are combined into compact groups and their size and coordinates are being determined. The obtained results are compared with the data of the AIS, Automatic Identification System of ships, and the results are displayed on a cartographic basis.
Article
This paper presents a segmentation algorithm for marine synthetic aperture radar (SAR) images. The proposed approach is based on the analysis of image sublooks along azimuth direction and exploits a novel indicator, called incoherent entropy, to divide the input targets into three classes, namely, ship, sea, and ambiguity. A global threshold detector is then implemented to discriminate between stable targets (ships), providing low incoherent entropy amplitude, and ambiguity or sea, implying very high and high values of the indicator, respectively. An integration of the segmentation algorithm into maritime surveillance systems is investigated, proposing its use as a discrimination tool to limit the false alarm rate of traditional prescreening algorithms. The main steps of a standard SAR-based ship detection system are thus implemented to provide a first screening of the candidate targets, which are, then, processed by sublook analysis using incoherent entropy to identify false detections. The proposed technique is tested on stripmap SAR images collected by the TerraSAR-X mission, over the Gulf of Naples, Italy. Algorithm detections are validated using ground-truth data, provided by automatic identification system. The results confirm the capability of the proposed discrimination approach to reject the vast majority of the false detections resulting from the prescreening algorithm.
Article
We demonstrate the preliminary results of ship detection application using synthetic aperture radar (SAR) and automatic identification system (AIS) together. Multi-frequency and multi-temporal SAR images such as TerraSAR-X and Cosmo-SkyMed (X-band), and Radarsat-2 (C-band) are acquired over the West Sea in South Korea. In order to compare with SAR data, we also collected an AIS data. The SAR data are pre-processed considering by the characteristics of scattering mechanism as for sea surface. We proposed the "Adaptive Threshold Algorithm" for classification ship efficiently. The analyses using the combination of the SAR and AIS data with time series will be very useful to ship detection or tracing of the ship.
Article
This paper proposes an Automatic Identification System (AIS) data aided Rayleigh constant false alarm rate (AIS-RCFAR) ship detection algorithm of multiple-target environment in synthetic aperture radar (SAR) images. This method aims to improve the detection performance in complex environment with the aid of AIS data. Traditional CFAR detectors generally use all the samples in the local background window for parameter estimation. However, in multiple-target environment, clutter edges and transition areas, due to the interference of the high-intensity outliers such as target pixels, ghosts, and other interfering pixels, the parameters are often overestimated, causing degradation of the detection performance. Aiming at solving this problem, AIS-RCFAR designs an adaptive-threshold based clutter trimming method with an adaptive-trimming-depth aided by AIS data to effectively eliminate the high-intensity outliers in the local background window while greatly sustaining the real sea clutter samples. Maximum-likelihood-estimator (MLE) with a closed-form solution is proposed to precisely estimate the parameters using the adaptively-trimmed clutter samples, the probability density function (PDF) of the sea clutter following Rayleigh distribution can be accurately modeled. AIS-RCFAR greatly enhances the detection rate (DR) in both homogeneous and non-homogeneous multiple-target environment, it also achieves a very low false alarm rate (FAR). In addition, the whole procedure of AIS-RCFAR is simple and efficient. Simulated data and real SAR images with corresponding matched AIS data are used for experiments to validate the superiority and feasibility of AIS-RCFAR.
Article
Ship detection is an important topic in remote sensing, and synthetic aperture radar (SAR) has a valuable contribution, allowing detection at nighttime and with almost any weather conditions. In addition, polarimetry can play a significant role considering its capability to discriminate between different targets. Recently, a new ship detector exploiting polarimetric information has been developed, namely, the Geometrical Perturbation–Polarimetric Notch Filter (GP–PNF). This work is focused on devising two statistical tests for the GP–PNF. The latter allow an automatic and adaptive selection of the detector threshold. Initially, the probability density function (pdf) of the detector is analytically derived. Finally, the Neyman–Pearson lemma is exploited to set the threshold calculating probabilities using the clutter pdf (i.e., a constant false-alarm rate) and a likelihood ratio. The goodness of fit of the clutter pdf is tested with four real SAR data sets acquired by the RADARSAT-2 and the TanDEM-X satellites. The former images are quad-polarimetric, whereas the latter are dual-polarimetric HH/VV. The data are accompanied by the Automatic Identification System (AIS) location of vessels, which facilitates the validation of the detection masks. It can be observed that the pdfs fit the data histograms, and they pass the two sample Kolmogorov–Smirnov and $chi^2$ tests.
Article
NOAA/NESDIS a initié le programme “Alaska SAR Demonstration” dont l'objectif est de faire la démonstration du potentiel des images RSO en bande C de RADARSAT-1 à fournir une information utile et en temps opportun sur l'environnement et pour la gestion des ressources pour des utilisateurs en Alaska. Un des produits développés dans le cadre du programme est une liste de localisations des navires. Cet article décrit l'algorithme développé pour générer ce produit par le biais de la détection automatique des navires basée sur des changements dans les statistiques locales. À l'aide d'images à basse résolution (100 mètres d'espacement), on démontre que l'on peut détecter des navires de dimension supérieure à 35 mètres (représentant 105 navires sur un total de 272 dans la zone test) avec un taux de fausse alerte de 0,01% pour une seule détection. Avec des images à haute résolution (50 mètres d'espacement), on peut détecter des navires d'une dimension supérieure à 32 mètres (représentant 124 navires sur 272) avec un taux de fausse alerte de 0,002% pour une seule détection. L'algorithme est entièrement automatisé et prend environ 10 minutes de temps-machine pour traiter une image ScanSAR en mode B large.
Article
The goal of the National Oceanic and Atmospheric Administration (NOAA) CoastWatch Program is to provide satellite and other environmental data and products for near-real-time monitoring of U.S. coastal waters in support of environmental science, management, and hazard response. During the last few years, products available through CoastWatch have expanded beyond the original infrared, visible, and sea surface temperature images to include ocean color, scatterometer wind, and synthetic aperture radar (SAR) images. A NOAA research and development program with partners in government, academia, and industry has endeavored to develop coastal ocean SAR applications for CoastWatch. Some of these applications, in particular wind measurement and hard target (i.e., vessel) detection, were developed for a preoperational demonstration. Users include the NOAA National Weather Service, the Alaska Department of Fish and Game, and the U.S. Coast Guard.
Validation of an automatic vessel detection algorithm using in-situ positions
  • K S Friedman
  • C Wackerman
  • F Funk
  • K Rowell
  • W G Pichel
  • P Clemente-Colón
  • X Li
Friedman, K. S., C. Wackerman, F. Funk, K. Rowell, W. G. Pichel, P. Clemente-Colón, and X. Li,, 2000, Validation of an automatic vessel detection algorithm using in-situ positions. Proceedings IGARSS 2000, 24-28 July 2000, Honolulu, Hawaii.
  • W Pichel
  • P Clemente-Colón
Pichel, W. and P. Clemente-Colón, 2000, NOAA CoastWatch SAR Applications and Demonstration, Johns Hopkins APL Technical Digest, 21(1), 49-57.