Remote sensing technology is an essential link in the global monitoring of the ocean surface and radars are efficient sensors for detecting maritime pollution. When used operationally by authorities, a tradeoff must usually be made between the covered area and the quantity of information collected by the radar. To identify the most appropriate imaging mode, a methodology based on Receiver Operating Characteristic (ROC) curve analysis has been applied to an original dataset collected by two airborne systems operating at L-band, both characterized by a very low instrument noise floor. The dataset was acquired during controlled releases of mineral and vegetal oil at sea. Various polarization-dependent quantities are investigated and their ability to detect slickcovered area is assessed. A relative ordering of the main polarimetric parameters is reported in this paper. When the sensor has a sufficiently low noise floor, HV is recommended because it provides SAR Imagery for Detecting Sea Surface Slicks: Performance Assessment of Polarimetric Parameters the strongest slick-sea contrast. Otherwise VV is found to be the most relevant parameter for detecting slicks on the sea surface. Among all the investigated quad-polarimetric settings, no significant added-value compared to single-pol data was found. More specifically, it is demonstrated, by increasing the instrument noise level, that the studied polarimetric quantities which combine the four polarimetric channels have performances of detection mainly driven by the NESZ. This result, obtained by progressively adding noise to the raw SAR data, indicates that the polarimetric discrimination between clean sea and polluted area results mainly from the differentiated behavior between single-bounce scattering and noise.

Ocean surface monitoring, emphasizing oil slick detection, has become essential due to its importance for oil exploration and ecosystem risk prevention. Automation is now mandatory since the manual annotation process of oil by photo-interpreters is time-consuming and cannot process the data collected continuously by the available spaceborne sensors. Studies on automatic detection methods mainly focus on Synthetic Aperture Radar (SAR) data exclusively to detect anthropogenic (spills) or natural (seeps) oil slicks, all using limited datasets. The main goal is to maximize the detection of oil slicks of both natures while being robust to other phenomena that generate false alarms, called “lookalikes”. To this end, this paper presents the automation of offshore oil slick detection on an extensive database of real and recent oil slick monitoring scenarios, including both types of slicks. It relies on slick annotations performed by expert photo-interpreters on Sentinel-1 SAR data over four years and three areas worldwide. In addition, contextual data such as wind estimates and infrastructure positions are included in the database as they are relevant data for oil detection. The contributions of this paper are: (i) A comparative study of deep learning approaches using SAR data. A semantic and instance segmentation analysis via FC-DenseNet and Mask R-CNN, respectively. (ii) A proposal for Fuse-FC-DenseNet, an extension of FC-DenseNet that fuses heterogeneous SAR and wind speed data for enhanced oil slick segmentation. (iii) An improved set of evaluation metrics dedicated to the task that considers contextual information. (iv) A visual explanation of deep learning predictions based on the SHapley Additive exPlanation (SHAP) method adapted to semantic segmentation. The proposed approach yields a detection performance of up to 94% of good detection with a false alarm reduction ranging from 14% to 34% compared to mono-modal models. These results provide new solutions to improve the detection of natural and anthropogenic oil slicks by providing tools that allow photo-interpreters to work more efficiently on a wide range of marine surfaces to be monitored worldwide. Such a tool will accelerate the oil slick detection task to keep up with the continuous sensor acquisition. This upstream work will allow us to study its possible integration into an industrial production pipeline. In addition, a prediction explanation is proposed, which can be integrated as a step to identify the appropriate methodology for presenting the predictions to the experts and understanding the obtained predictions and their sensitivity to contextual information. Thus it helps them to optimize their way of working.

This paper introduces a method for offshore oil slick detection. At present, Synthetic Aperture Radar (SAR) is an image acquisition technology useful for oil slick detection in all weather conditions. It is used to carry out the detection, with notable limitations under certain conditions (surfaces, weather conditions). Manual SAR images analysis is expensive and, given the increasing amount of data collected from available sensors, automation becomes mandatory. To achieve this objective, instance object detection relying on deep neural networks is interesting to adapt to the data variability. Relying on such an approach, this article explores the capabilities of generalizing the detection of slicks on large datasets using the Mask-RCNN model. A detailed performance analysis is established in two complementary directions: (i) the impact of the SAR image characteristics(sensor, geographical areas, lookalike presence), (ii) the impact of the neural network architecture, transferred capabilities and training procedures. The main findings of this analysis show that Mask-RCNN features promising performance for pollution detection.

No abstract