ERCIM “ Alain Bensoussan ” Fellowship Scientific Report

The Texture Fragmentation and Reconstruction (TFR) algorithm has been recently introduced to address the problem of image segmentation by textural properties, based on a suitable image description tool known as the Hierarchical Multiple Markov Chain (H-MMC) model. TFR provides a hierarchical set of nested segmentation maps by first identifying the elementary image patterns, and then merging them sequentially to identify complete textures at different scales of observation. In this work, we propose a major modification to the TFR by resorting to a graph based description of the image content and a graph clustering technique for the enhancement and extraction of image patterns. A procedure based on mathematical morphology will be introduced that allows for the construction of a colour-wise image representation by means of multiple graph structures, along with a simple clustering technique aimed at cutting the graphs and correspondingly segment groups of connected components with a similar spatial context. The performance assessment, realized both on synthetic compositions of real-world textures and images from the remote sensing domain, confirm the effectiveness and potential of the proposed method. The following paper has been prepared for forthcoming conferences, but not yet submitted: R.Gaetano, G.Scarpa, J.Zerubia, “Morphological Road Segmentation in Urban Areas from High Resolution Satellite images”, to be submitted. Abstract: High resolution satellite images provided by the last generation sensors significantly increased the potential of almost all the image information mining (IIM) applications related to earth observation. This is especially true for the extraction of road information, task of primary interest for many remote sensing applications, which scope is more and more extended to complex urban scenarios thanks to the availability of highly detailed images. This context is particularly challenging due to such factors as the variability of road visual appearance and the occlusions from entities like trees, cars and shadows. On the other hand, the peculiar geometry and morphology of man-made structures, particularly relevant in urban areas, is enhanced in high resolution images, making this kind of information especially useful for road detection. In this work, we provide a new insight on the use of morphological image analysis for road extraction in complex urban scenarios, and propose a technique for road segmentation that only relies on this domain. The key point of the technique is the use of skeletons as powerful descriptors for road objects: the proposed method is based on an ad-hoc skeletonization procedure that enhances the linear structure of road segments, and extracts road objects by first detecting their skeletons and then associating each of them with a region of the image. High resolution satellite images provided by the last generation sensors significantly increased the potential of almost all the image information mining (IIM) applications related to earth observation. This is especially true for the extraction of road information, task of primary interest for many remote sensing applications, which scope is more and more extended to complex urban scenarios thanks to the availability of highly detailed images. This context is particularly challenging due to such factors as the variability of road visual appearance and the occlusions from entities like trees, cars and shadows. On the other hand, the peculiar geometry and morphology of man-made structures, particularly relevant in urban areas, is enhanced in high resolution images, making this kind of information especially useful for road detection. In this work, we provide a new insight on the use of morphological image analysis for road extraction in complex urban scenarios, and propose a technique for road segmentation that only relies on this domain. The key point of the technique is the use of skeletons as powerful descriptors for road objects: the proposed method is based on an ad-hoc skeletonization procedure that enhances the linear structure of road segments, and extracts road objects by first detecting their skeletons and then associating each of them with a region of the image. Experimental results are presented on two different high resolution satellite images of urban