Antonis Katartzis

A model-based approach to the automatic extraction of linear features from airborne images

The authors describe a model-based method for the automatic extraction of linear features, like roads and paths, from aerial images. The paper combines and extends two earlier approaches for road detection in SAR satellite images and presents the modifications needed for the application domain of airborne image analysis together with representative results.

A Stochastic Framework for the Identification of Building Rooftops Using a Single Remote Sensing Image

The identification of building rooftops from a single image, without the use of auxiliary 3-D information like stereo pairs or digital elevation models, is a very challenging and difficult task in the area of remote sensing. The existing methodologies rarely tackle the problem of 3-D object identification, like buildings, from a purely stochastic viewpoint. Our approach is based on a stochastic image interpretation model, which combines both 2-D and 3-D contextual information of the imaged scene. Building rooftop hypotheses are extracted using a contour-based grouping hierarchy that emanates from the principles of perceptual organization. We use a Markov random field model to describe the dependencies between all available hypotheses with regard to a globally consistent interpretation. The hypothesis verification step is treated as a stochastic optimization process that operates on the whole grouping hierarchy to find the globally optimal configuration for the locally interacting grouping hypotheses, providing also an estimate of the height of each extracted rooftop. This paper describes the main principles of our method and presents building detection results on a set of synthetic and airborne images.

A hierarchical Markovian model for multiscale region-based classification of vector-valued images

We propose a new classification method for vector-valued images, based on: 1) a causal Markovian model, defined on the hierarchy of a multiscale region adjacency tree (MRAT), and 2) a set of nonparametric dissimilarity measures that express the data likelihoods. The image classification is treated as a hierarchical labeling of the MRAT, using a finite set of interpretation labels (e.g., land cover classes). This is accomplished via a noniterative estimation of the modes of posterior marginals (MPM), inspired from existing approaches for Bayesian inference on the quadtree. The paper describes the main principles of our method and illustrates classification results on a set of artificial and remote sensing images, together with qualitative and quantitative comparisons with a variety of pixel-based techniques that follow the Bayesian-Markovian framework either on hierarchical structures or the original image lattice.

Application of Mathematical Morphology and Markov Random Field Theory to the Automatic Extraction of Linear Features in Airborne Images

In this paper we present a model-based approach to the automatic extraction of linear features, like roads and paths, from aerial optical images. The proposed method consists of two steps. The first step utilizes local information related to the geometry and radiometry of the structures to be extracted. It consists of a series of morphological filtering stages. The resulting image (response) serves as input to a line-following algorithm, which produces a set of line segments. In the second step, a segment linking process is carried out incorporating contextual, a priori knowledge about the road shape, with the use of Markov random field (MRF) theory. In this approach the extracted line segments, produced by the morphological operators, are organized as a graph. The linking of these segments is then achieved through assigning labels to the nodes of the graph, using domain knowledge, extracted line segments measurements and spatial relationships between the various line segments. The interpretation labels are modeled as a MRF on the corresponding graph and the linear feature identification problem is formulated as a maximum a posteriori (MAP) estimation rule. The proposed approach has been successfully applied to airborne images of different profile

A Bayesian approach to nonlinear diffusion based on a Laplacian prior for ideal image gradient

We study the relationships between diffusivity functions in a nonlinear diffusion scheme and probabilities of edge presence under a marginal prior on ideal, noise-free image gradient. In particular we impose a Laplacian-shaped prior for the ideal gradient and we define the diffusivity function explicitly in terms of edge probabilities under this prior. The resulting diffusivity function has no free parameters to optimize. Our results demonstrate that the new diffusivity function, automatically, i.e., without any parameter adjustments, satisfies the well accepted criteria for the goodness of edge-stopping functions. Our results also offer a new and interesting interpretation of some widely used diffusivity functions, which are now compared to edge-stopping functions under a marginal prior for the ideal image gradient

Detection of buildings from a single airborne image using a Markov random field model

We propose an automated method for the detection of buildings from a single airborne color optical image using a dedicated Markov random field model, which describes both geometric and photometric attributes of the 3-D objects of interest. The paper presents the basic principles and some preliminary results of our approach.

A Bayesian formulation of edge-stopping functions in nonlinear diffusion

We propose a novel, Bayesian formulation of the edge-stopping (diffusivity) function in a nonlinear diffusion scheme in terms of edge probability under a marginal prior on noise-free gradient. This formulation differs from the existing probabilistic diffusion approaches that give stochastic formulations for the conductivity but not for the diffusivity function of the gradient. In particular, we impose a Laplacian prior for the ideal gradient, but the proposed formulation is general and can be used with other marginal distributions. We also make links to related works that treat correspondences between nonlinear diffusion and wavelet shrinkage

Model-based technique for the measurement of skin thickness in mammography

A model-based method is proposed for the measurement of breast skin thickness from digitised mammograms that takes into account both the geometric and radiographic properties of the skin region. The method initially identifies a salient feature that discriminates the skin from the other anatomical structures of the breast. Its identification is based on a multi-scale grey-level gradient estimation, using a wavelet decomposition of the image. The spatial distribution of this feature is organised as a graph, with each of its nodes associated with a binary set of interpretation labels. A Markov randomfield is defined on the set of labels, and the best graph labelling is finally determined with a maximum a posteriori (MAP) probability criterion. The method was applied on 11 mammograms with improved contrast characteristics at the breast periphery, obtained by an exposure equalisation technique during image acquisition. The validation of the approach was performed by calculating the root mean square (RMS) error between the detected skin thickness and manual measurements performed on each of the films. The resulting error values ranged from 0.1 mm to 0.2 mm for normal cases and reached a maximum of 0.5 mm in pathological cases with advanced skin thickening.

Statistical models for multidisciplinary applications of image segmentation and labelling

Three classes of statistical techniques used to solve image segmentation and labelling problems are reviewed: (1) supervised and unsupervised pixel classification, (2) exploitation of the probability distribution map as a way to model image structure, (3) Markov random field modelling combined with MAP statistical classification. Diverse examples illustrate the potential of the three approaches that are described as generic methods belonging to a common framework for image segmentation/labelling.

A hierarchical Markovian model for multiscale region-based classification of multispectral images

We propose a new multispectral image classification method, based on a Markovian model, defined on the hierarchy of a multiscale region adjacency graph. The paper describes the main principles of our method and illustrates classification results on a set of artificial and remote sensing images, together with qualitative and quantitative comparisons with a variety of multi-and single-resolution Bayesian classification approaches.