Paul C. Smits

The European geoportal––one step towards the establishment of a European Spatial Data Infrastructure

Abstract The European Geoportal has been identified as one of the building blocks of a European Spatial Data Infrastructure (ESDI). The vision of the EU Geoportal is to allow users to discover, understand, view, access, and query geographic information of their choice from the local level to the global level, for a variety of uses, such as environmental policy development and impact assessment, land use planning, natural disasters preparedness, monitoring, and response. The EU Geoportal will facilitate links and coherence with many institutional servers and portals and will provide on-line access to collections of spatial data and services supplied by multiple public and private organisations. This paper presents some of the work associated with the establishment of an ESDI, and the requirements for the EU Geoportal. The prototype version of the EU Geoportal demonstrates the feasibility to link distributed geographic information services but at the same time reveals a number of challenges that need to be considered in the path towards interoperability. The current obstacles related to technological interoperability issues are discussed in detail and proposals are made for the next steps to be taken to speed up the implementation of the ESDI.

Synthetic aperture radar image segmentation by a detail preserving Markov random field approach

A multichannel image segmentation method is imposed that utilizes Markov random fields (MRFs) with adaptive neighborhood (AN) systems. Bayesian inference is applied to realize the combination of evidence from different knowledge sources. In such a way, optimization of the shape of a neighborhood system is achieved by following a criterion that makes use of the Markovian property exploiting the local image content. The MRF segmentation approach with AN systems (MRF-AN) makes it possible to better preserve small features and border areas. The purpose of the paper is to show the usefulness of the concept of MRF-AN for SAR image segmentation.

Toward specification-driven change detection

A change-detection methodology based on explicit user requirements in terms of example imagery and false alarm and misclassification probabilities is discussed and applied. A distance measure between texture features is defined, and its ability is illustrated to measure changes in urban areas in high resolution, panchromatic, spaceborne images.

Foreword special issue on analysis of multitemporal remote sensing images

T HE development of effective methodologies for the analysis of multitemporal data is one of the most important and challenging issues that the remote sensing community should face in the next years. The importance and timeliness of this issue are directly related to the ever-increasing quantity of multitemporal data provided by the numerous remote sensing satellites that orbit around our planet. These data are captured by different kinds of sensors (e.g., multispectral or synthetic aperture radar (SAR) sensors) and have different geometrical properties. The temporal component, integrated with the spectral and the spatial dimensions, may result in a valuable information source that, if properly exploited, allows revealing complex and important patterns that are the concern of applications connected with environmental monitoring and analysis of land-cover dynamics. However, the use of the temporal domain further increases the complexity usually associated with the processing of single-date remote sensing images. In this context, the definition of automatic and semiautomatic techniques for data preprocessing and analysis is a crucial component for the development of operational tools based on multitemporal remote sensing data and, thus, for the value chain of geospatial information as a whole. An important issue that should be considered in the definition of such techniques is that the analysis of multitemporal images cannot be carried out in an efficient way by applying to multitemporal data methodologies developed for analyzing single-date images. On the contrary, the presence of the temporal dimension should be properly considered by integrating in the data processing procedures algorithms capable of exploiting the relationships between images acquired on the same geographical area at different times. The solution of this complex methodological problem can result in an increase of the accuracy provided from the data analysis process. It is worth underlining that despite the term “analysis of multitemporal images” implicitly addressing specific methodological problems related to the temporal domain (like change detection, detection of land-cover transitions, shape change detection, analysis of changes in the temporal signature extracted from long series of images), it is also related to more classical pattern recognition problems (e.g., single-date classification), whose solution can benefit from the exploitation of multitemporal information.

Discontinuity-adaptive Markov random field model for the segmentation of intensity SAR images

An approach for the segmentation of synthetic aperture radar (SAR) intensity images is discussed. The method integrates the gamma distribution in an objective function that exploits a discontinuity-adaptive Markov random field (DA-MRF) model that allows the user to determine the degree of homogeneity of the results according to the nature of the phenomena of interest. Both visual and numerical results illustrate its potential.

Modelling the histograms of various classes in SAR images

Abstract A new model for the distribution of grey level values for different classes is proposed, for use with synthetic aperture radar (SAR) images. It takes into consideration noise, pixel saturation and intraclass variability.

Exploiting spatial correlation features for SAR image analysis

Spatial information is of great importance in Synthetic Aperture Radar (SAR) image analysis and recently, many methods have been developed that take this feature into account. This paper deals with a supervised approach to SAR image classification that exploits spatial features within a hierarchical classification framework. In contrast to the classical approach, which makes the hypothesis about sample data independence, in the proposed method, the spatial dependence of neighboring pixels is taken into account to estimate relatively simple statistical features such as sample spatial mean and sample spatial variance, thus allowing contextual information to be easily handled. The Bhattacharyya distribution distance is used during the training phase, and the generated tree is applied during the test phase. After this, both phases are based on the proposed features. As a result, second-order statistics play a major role in the present classification problem. Experimental results on different SAR data sets are reported. It is shown that the accuracy of the proposed method is better than that of the hit classifier and that the new method is also computationally more convenient.

ISO/TC211: Standardisation of geographic information and geo-informatics

The scope of ISO/TC211 is standardisation in the field of digital geographic information (GI). TC211s work aims to establish a structured set of standards for information concerning objects or phenomena that are directly or indirectly associated with a location relative to the Earth. These standards may specify, for geospatial information, methods, tools and services for data management, acquiring, processing, analysing, accessing, presenting and transferring such data in digital/electronic form between different users, systems and locations. The aim of this article is threefold: (1) to provide some background information about why efforts are made to standardise GI and geomatics, (2) to report on which GI standards have reached and advanced stage of consensus under ISO authority, and (3) to show the relevance of these standards for advancing remote sensing and related fields.

Information fusion in a Markov random field-based image segmentation approach using adaptive neighbourhoods

In this paper an image segmentation method is proposed that is a modification to the Markov random field (MRF) region label process used by Rignot and Chellappa (1992). Using Bayesian inference, the optimal shape of the neighbourhood system is determined on the basis of the Markovian property. This MRF segmentation approach with adaptive neighbourhood systems (MRF-AN) makes it possible to better preserve small features by the combination of evidence from different knowledge sources. The purpose of the article is to show the validity of the concept of MRF-AN for image segmentation. Results are shown using synthetic aperture radar data.

An irregular MRF region label model for multi-channel image segmentation

Abstract A multi-channel image segmentation method is discussed that utilizes a Markov random field (MRF) region label model with adaptive neighbourhoods. Bayesian inference is applied to realize the combination of evidence from different knowledge sources. In such a way, optimization of the shape of a neighbourhood set is achieved by following a criterion that makes use of hypothesis on the Markovian property by exploiting the local image content. The purpose of the article is to show the theoretical validity of the approach by elucidating correspondences and differences with a similar concept. Results are shown using optical remote sensing data.