Grégoire Mercier

AIS-Based Evaluation of Target Detectors and SAR Sensors Characteristics for Maritime Surveillance

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.

Performance evaluation of Sentinel-1 data in SAR ship detection

This study addresses the performances of ship detection with data acquired by the newly launched Sentinel-1 SAR sensor. An automatic validation approach based on coastal AIS data is employed for measuring the detection efficiency. Results are compared with ship detection capabilities conducted on Radarsat-2 and CosmoSkymed datasets. The influence of different key parameters, such as SAR imaging characteristics (polarization, incidence angle) or meteorological conditions, is addressed. Such an analysis is useful for operational services to determine data specifications that assure optimum vessel detection for maritime surveillance applications.

Multiscale Event-Based Mining in Geophysical Time Series: Characterization and Distribution of Significant Time-Scales in the Sea Surface Temperature Anomalies Relatively to ENSO Periods from 1985 to 2009

In this paper, one-dimensional (1-D) geophysical time series are regarded as series of significant time-scale events. We combine a wavelet-based analysis with a Gaussian mixture model to extract characteristic time-scales of 486 144 detected events in the Sea Surface Temperature Anomaly (SSTA) observed from satellite at global scale from 1985 to 2009. We retrieve four low-frequency characteristic time-scales of Niño Southern Oscillation (ENSO) in the 1.5- to 7-year range and show their spatial distribution. High-frequency (HF) SSTA event spatial distribution shows a dependency to the ENSO regimes, pointing out that the ENSO signal also involves specific signatures at these time-scales. These fine-scale signatures can hardly be retrieved from global EOF approaches, which tend to exhibit uppermost the low-frequency influence of ENSO onto the SSTA. In particular, we observe at global scale a major increase by 11% of the number of SSTA HF events during Niño periods, with a local maximum of 80% in Europe. The methodology is also used to highlight an ENSO-induced frequency shift during the major 1997-2000 ENSO event in the intertropical Pacific. We observe a clear shift from the high frequencies toward the 3.36-year scale with a maximum shift occurring 2 months before the ENSO maximum of energy at 3.36-year scale.

Synergy of Sentinel-1 and Sentinel-2 imagery for wetland monitoring information extraction from continuous flow of sentinel images applied to water bodies and vegetation mapping and monitoring

Wetlands, very sensitive and valuable ecosystem can be monitored in terms of water surfaces dynamics as well as vegetation characterisation and monitoring exploiting satellite data. The synergy between the recently launched Sentinel1 and Sentinel2 satellites have been investigated over the Poyang and Anhui lakes in PR China. Results highlight the gain in terms of operationality with a very high revisit exploiting the two systems, as well as for a thematic point of view with no was not yet reach at this resolution for water bodies and terrestrial, floating and submerged vegetation mapping and monitoring.

High order structural image decomposition by using non-linear and non-convex regularizing objectives

The paper addresses structural decomposition of images by using a family of non-linear and non-convex objective functions. These functions rely on p quasi-norm estimation costs in a piecewise constant regularization framework. These objectives make image decomposition into constant cartoon levels and rich textural patterns possible. The paper shows that these regularizing objectives yield image texture-versus-cartoon decompositions that cannot be reached by using standard penalized least square regularizations associated with smooth and convex objectives.

Characterization of Time-Varying Regimes in Remote Sensing Time Series: Application to the Forecasting of Satellite-Derived Suspended Matter Concentrations

The spatial and temporal coverage of satellites provides data that are particularly well suited for the analysis and characterization of space-time-varying geophysical relationships. The latent-class models aim here to identify time-varying regimes within a dataset. This is of particular interest for geophysical processes driven by the seasonal variability. As a case example, we study the daily concentration of mineral suspended particulate matters estimated from satellite-derived datasets, in coastal waters adjacent to the French Gironde river mouth. We forecast this high-resolution dataset using environmental data (wave height, wind strength and direction, tides, and river outflow) and four latent-regime models: homogeneous and nonhomogeneous Markov-switching models, with and without an autoregressive term (i.e., the mineral suspended matter concentration observed the day before). Using a validation dataset, significant improvements are observed with the multiregime models compared to a classical multiregression and a state-of-the-art nonlinear model [support vector regression (SVR) model]. The best results are reported for a mixture of three regimes for the autoregressive model using nonhomogeneous transitions. With the autoregressive models, we obtain at day+1 for the mixture model forecasting performances of 93% of the explained variance, compared to 83% for a standard linear model and 85% using an SVR. These improvements are more important for the nonautoregressive models. These results stress the potential of the identification of geophysical regimes to improve the forecasting. We also show that nonhomogeneous transition probabilities and estimated autoregressive terms improve forecasting performances when observation data is lacking for short-time period of 1-15 days.

Ship detection in SAR medium resolution imagery for maritime surveillance: Algorithm validation using AIS data

In this paper paper we address performances of ship detection algorithms in medium resolution SAR imagery. An automatic validation approach based on coastal AIS data allows to evaluate detectors efficiency. Detection capabilities remain sensitive to dataset features such as SAR imaging characteristics, meteorological conditions or vessel size. The influence of this different key parameters is fully assessed in this study. This analysis is valuable for operational services, allowing to select the most appropriate type of data for different applications in maritime surveillance.

Unmixing polarimetric radar images based on land cover type before target decomposition

A new method for unmixing radar polarimetric images with optical images is proposed. It was found that the polarimetric covariance matrix can be unmixed considering a linear model. As a result, this model is used to produce unmixed covariance matrices based on land cover types. We hope to prove that this unmixing of the polarimetric information produce greater information for land cover classification.

Convolutional Neural Networks for object recognition on mobile devices: A case study

Deep Learning (DL), especially Convolutional Neural Networks (CNN), has become the state-of-the-art for a variety of pattern recognition issues. Technological developments have allowed the use of high-end General Purpose Graphic Processor Units (GPGPU) for accelerating numerical problem solving. They resort no only to lower computational time, but also allow considering much larger networks. Hence, nowadays computers are able to drive deeper, wider and more powerful models. State of the art CNNs have achieved human-like performance in several recognition tasks such as: handwritten character recognition, face recognition, scene labelling, object detection and image classification among others. Meanwhile, mobile devices have become powerful enough to handle the computations required for deploying CNNs models in near real-time. Here, we investigate the implementation of light-weight CNN schemes on mobile devices for domain-specific objection recognition tasks.

Assimilative 2-D Lagrangian Transport Model for the Estimation of Oil Leakage Parameters From SAR Images: Application to the Montara Oil Spill

Indonesia is particularly vulnerable to oil spill since Indonesian waters, which account for 80% of its territory, involve a very active maritime traffic and a large number of onshore and offshore oil platforms. Within the framework of Infrastructure Development Space Oceanography project, we address the operational synthetic aperture radar (SAR) based monitoring of oil spill in Indonesian waters from space. This work focuses on the assimilation of SAR observations into a 2-D Lagrangian trajectory model. The simulated surface oil trajectories are compared to the satellite observations in subsequent forecast cycles for veracity testing by estimating best leakage parameters of detected oil spills. As a case study, we consider a large oil spill event that took place in Indonesian waters in Fall 2009, referred to as the Montara oil spill. A novel methodology has been developed, which combines SAR-based oil spill detection using a Lagrangian analysis and numerical tools. Our model relies on four key parameters: wind-related and current-related drift parameters, and the origin and the duration of the oil leakage. Given an SAR-derived oil spill detection, a numerical inversion is used to optimize these model parameters, so that the simulated drift matches the SAR-derived observation. The demonstration of the relevance of the proposed scheme for the Montara oil spill and further discussion on operational interest for satellite-based oil spill monitoring can be useful in rapid response system in Indonesia.