Konstantinos Topouzelis

An object‐oriented methodology to detect oil spills

A new automated methodology for oil spill detection is presented, by which full synthetic aperture radar (SAR) high‐resolution image scenes can be processed. The methodology relies on the object‐oriented approach and profits from image segmentation techniques to detected dark formations. The detection of dark formations is based on a threshold definition that is fully adaptive to local contrast and brightness of large image segments. For the detection process, two empirical formulas are developed that also permit the classification of oil spills according to their brightness. A fuzzy classification method is used to classify dark formations as oil spills or look‐alikes. Dark formations are not isolated and features of both dark areas and sea environment are considered. Various sea environments that affect oil spill shape and boundaries are grouped in two knowledge bases, used for the classification of dark formations. The accuracy of the method for the 12 SAR images used is 99.5% for the class of oil spills, and 98.8% for that of look‐alikes. Fresh oil spills, fresh spills affected by natural phenomena, oil spills without clear stripping, small linear oil spills, oil spills with broken parts and amorphous oil spills can be successfully detected.

Investigation of genetic algorithms contribution to feature selection for oil spill detection

Oil spill detection methodologies traditionally use arbitrary selected quantitative and qualitative statistical features (e.g. area, perimeter, complexity) for classifying dark objects on SAR images to oil spills or look‐alike phenomena. In our previous work genetic algorithms in synergy with neural networks were used to suggest the best feature combination maximizing the discrimination of oil spills and look‐alike phenomena. In the present work, a detailed examination of robustness of the proposed combination of features is given. The method is unique, as it searches though a large number of combinations derived from the initial 25 features. The results show that a combination of 10 features yields the most accurate results. Based on a dataset consisting of 69 oil spills and 90 look‐alikes, classification accuracies of 85.3% for oil spills and in 84.4% for look‐alikes are achieved.

Dark formation detection using neural networks

Synthetic Aperture Radar (SAR) images are extensively used for dark formation detection in marine environment, as they are not affected by local weather conditions and cloudiness. Dark formations can be caused by man‐made actions (e.g. oil spills) or natural ocean phenomena (e.g. natural slicks and wind front areas). Radar backscatter values for oil spills are very similar to backscatter values for very calm sea areas and other ocean phenomena because they dampen the capillary and short gravity sea waves. Thus, traditionally, dark formation detection is the first stage of the oil‐spill detection procedure and in most studies is performed manually or using a fixed size window in which a threshold value is adopted. In high‐resolution imagery, dark formation detection may fail due to the nonlinear behaviour of the pixel values contained in the dark formation and in the area around it. In this paper, we examine the ability of two feed‐forward neural network families, i.e. Multilayer Perceptron (MLP) and the Radial Basis Function (RBF) networks, to detect dark formations in high‐resolution SAR images. The general objective of this paper is to test the potential of artificial neural networks for dark formation detection using SAR high‐resolution satellite images. Both the type and the architecture of the network are subjects of research. The inputs into the networks are the original SAR images. Each network is called to classify an area of the image as dark area or sea. The group of MLP networks can be recognized as the most suitable group for dark formation detection, as it presents reliable stable results for all the examined accuracies. Nevertheless, in terms of single topology, there is no an MLP topology that performs significantly better than the others.

Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes

Radar backscatter values from oil spills are very similar to backscatter values from very calm sea areas and other ocean phenomena. Several studies aiming at oil spill detection have been conducted. Most of these studies rely on the detection of dark areas, which have high Bayesian probability of being oil spills. The drawback of these methods is a complex process, mainly because non-linearly separable datasets are introduced in statistically based decisions. The use of neural networks (NNs) in remote sensing has increased significantly, as NNs can simultaneously handle non-linear data of a multidimensional input space. In this article, we investigate the ability of two commonly used feed-forward NN models: multilayer perceptron (MLP) and radial basis function (RBF) networks, to classify dark formations in oil spills and look-alike phenomena. The appropriate training algorithm, type and architecture of the optimum network are subjects of research. Inputs to the networks are the original synthetic aperture radar image and other images derived from it. MLP networks are recognized as more suitable for oil spill detection.

Coastline Zones Identification and 3D Coastal Mapping Using UAV Spatial Data

Spatial data acquisition is a critical process for the identification of the coastline and coastal zones for scientists involved in the study of coastal morphology. The availability of very high-resolution digital surface models (DSMs) and orthophoto maps is of increasing interest to all scientists, especially those monitoring small variations in the earth’s surface, such as coastline morphology. In this article, we present a methodology to acquire and process high resolution data for coastal zones acquired by a vertical take off and landing (VTOL) unmanned aerial vehicle (UAV) attached to a small commercial camera. The proposed methodology integrated computer vision algorithms for 3D representation with image processing techniques for analysis. The computer vision algorithms used the structure from motion (SfM) approach while the image processing techniques used the geographic object-based image analysis (GEOBIA) with fuzzy classification. The SfM pipeline was used to construct the DSMs and orthophotos with a measurement precision in the order of centimeters. Consequently, GEOBIA was used to create objects by grouping pixels that had the same spectral characteristics together and extracting statistical features from them. The objects produced were classified by fuzzy classification using the statistical features as input. The classification output classes included beach composition (sand, rubble, and rocks) and sub-surface classes (seagrass, sand, algae, and rocks). The methodology was applied to two case studies of coastal areas with different compositions: a sandy beach with a large face and a rubble beach with a small face. Both are threatened by beach erosion and have been degraded by the action of sea storms. Results show that the coastline, which is the low limit of the swash zone, was detected successfully by both the 3D representations and the image classifications. Furthermore, several traces representing previous sea states were successfully recognized in the case of the sandy beach, while the erosion and beach crests were detected in the case of the rubble beach. The achieved level of detail of the 3D representations revealed new beach characteristics, including erosion crests, berm zones, and sand dunes. In conclusion, the UAV SfM workflow provides information in a spatial resolution that permits the study of coastal changes with confidence and provides accurate 3D visualizations of the beach zones, even for areas with complex topography. The overall results show that the presented methodology is a robust tool for the classification, 3D visualization, and mapping of coastal morphology.

Assembling ecological pieces to reconstruct the conservation puzzle of the aegean sea

The effective conservation of marine biodiversity through an integrated ecosystem-based management approach requires a sound knowledge of the spatial distribution of habitats and species. Although costly in terms of time and resources, acquiring such information is essential for the development of rigorous management plans and the meaningful prioritization of conservation actions. Located in the northeastern part of the Mediterranean, the Aegean Sea represents a stronghold for marine biodiversity. However, conservation efforts are hampered by the apparent lack of spatial information regarding marine habitats and species. This work is the first to address this knowledge gap by assembling, updating, and mapping information on the distribution of key ecological components. A range of data sources and methodological approaches was utilized to compile and complement the available data on 68 ecological features of conservation interest (58 animal species, six habitat categories, and four other vulnerable ecological features). A standardized data evaluation procedure was applied, based on five semi-quantitative data quality indicators in the form of a pedigree matrix. This approach assessed the sufficiency of the datasets and allowed the identification of the main sources of uncertainty, highlighting aspects that require further investigation. The overall dataset was found to be sufficient in terms of reliability and spatiotemporal relevance. However, it lacked in completeness, showing that there are still large areas of the Aegean that remain understudied, while further research is needed to elucidate the distribution patterns and conservation status of several ecological features; especially the less charismatic ones and those found in waters deeper than 40 m. Moreover, existing conservation measures appear to be inadequate to safeguard biodiversity. Only 2.3% of the study area corresponds to designated areas for conservation, while 41 of the ecological features are underrepresented in these areas. Considering the high geomorphological complexity and transnational character of the Aegean Sea, this study does not offer a complete account of the multifaceted diversity of this ecoregion. Instead, it represents a significant starting point and a solid basis for the development of systematic conservation plans that will allow the effective protection of biodiversity within an adaptive management framework.

Incidence angle normalization of Wide Swath SAR data for oceanographic applications

Abstract A backscattering trend in the range direction of the signal received by Synthetic Aperture Radar (SAR) in Wide Swath (WS) mode results in a progressive reduction of brightness over images from near to far range, which affects the detection and classification of sea surface features on wide swath SAR images. The aim of the present paper is to investigate methods for limiting the issue of Normalized Radar Cross-Section (NRCS or σ°) variation due to the incidence angle. Two sensor independent functions are investigated: a theoretical backscattering shape function derived from a minimum wind speed and an empirical range fit of NRCS against incidence angle θ. The former method exploits only the modeled NRCS values while the latter only the image content. The results were compared with the squared cosine correction, the most widely applied method for normalization, using six newly developed comparison factors. The results showed that the cosine squared normalization has the lowest efficiency while the proposed methods have similar behaviors and comparable results. Nevertheless, after the log-transformation and summation of the comparison factors, it was clearly shown that theoretical normalization performance is superior to the empirical one since it has the highest accuracy and requires less computational time.

Seagrass mapping in Greek territorial waters using Landsat-8 satellite images

Abstract Seagrass meadows are among the most valuable coastal ecosystems on earth due to their structural and functional roles in the coastal environment. This study demonstrates remote sensing’s capacity to produce seagrass distribution maps on a regional scale. The seagrass coverage maps provided here describe and quantify for the first time the extent and the spatial distribution of seagrass meadows in Greek waters. This information is needed for identifying priority conservation sites and to help coastal ecosystem managers and stakeholders to develop conservation strategies and design a resilient network of protected marine areas. The results were based on an object-based image analysis of 50 Landsat-8 satellite images. The time window of image acquisition was between June 2013 and July 2015. In total, the seagrass coverage in Greek waters was estimated at 2619 km2. The largest coverages of individual seagrass meadows were found around Lemnos Island (124 km2), Corfu Island (46 km2), and East Peloponnese (47 km2). The accuracy assessment of the detected areas was based on 62 Natura 2000 sites, for which habitat maps were available. The mean total accuracy for all 62 sites was estimated at 76.3%.

Mapping coastal marine habitats and delineating the deep limits of the Neptune’s seagrass meadows using very high resolution Earth observation data

ABSTRACT Seagrass meadows are one of the most important coastal habitats across the globe. These are mainly constituted by the marine plants of the genus Posidonia and Thalassia. In the Mediterranean Sea, Posidonia oceanica is the dominant endemic plant that affects physical, biogeochemical, and biological processes. The decline in the spatial distribution has been attributed to excessive anthropic pressures and other large-scale environmental changes. The monitoring of the spatial distribution requires an update and accurate seagrass meadows delineation, i.e. meadow edge marking with a replicable method. The present study aims to present an approach to support the coastal marine habitat mapping, under the scheme of the Natura 2000 network using very high resolution Earth observation data and to prove that satellite images can be used for the mapping of the deep limits of the seagrass meadows. Pixel-based classification and object-oriented image analysis have been implemented for the image classification. Pixel-based Support Vector Machines and object-based Nearest Neighbor classifiers provided the best results with an overall accuracy of more than 90%, while deep limits have been successfully identified and separated from the deep waters.

Spiral eddies in the Aegean Sea derived by satellite radar data

Ocean mesoscale spiral eddies is a phenomenon that came apparent in the last 50 years but until today there are many questions yet to be answered about their formation, distribution and correlation to the dynamical processes on the sea surface. Main objective of the present paper is to provide an extensive analysis on the occurrence and statistics of smallmesoscale eddies over the Aegean Sea using synthetic aperture radar (SAR) images. The study area is characterized from unique hydro-dynamical and topographical conditions that give another aspect on the phenomenon. Present study based on 169 medium resolution (WSM) ENVISAT ASAR images acquired in 2011. As a result of the analysis 192 eddies formations were detected. The majority of those eddies were visualized due to the presence of surfactant films (black eddies) on sea surface and majority of them were cyclonically rotating. The diameter of the observed formations of eddies was within 1 to 16 km. The detected eddies were classified by categories depending on their shape and their generation mechanism. Seasonal and spatial distribution is presented, in order to understand their variability compared with the upper surface circulation. The value of the baroclinic Rossby radius of deformation was used for the discrimination of wind driven or geostrophic balanced spiral eddies. Though most of the observed formations seem to be wind driven, an important correlation with the upper circulation of the Aegean Sea is shown.