Elisabetta Binaghi | Università degli Studi dell'Insubria (original) (raw)

Papers by Elisabetta Binaghi

In our societies livestock grazing has a disgusted smell. It was the reason for the soil loss in ... more In our societies livestock grazing has a disgusted smell. It was the reason for the soil loss in the Mediterraneans, it was the reason for the degradation of forests in Central Europe in historic times, and it is the driving force for the clearcutting of primeveal forests in developing and underdeveloped countries. Pictures of over-grazed land in arid zones come into our minds, the soils unprotectedly exposed to the eroding powers of wind and water. In Europe livestock, like no other human activity, coined cultures and landscapes over more than 5 000 years. Like in other continents it was not always a kind of use which we would call “sustainable” in modern interpretation. However, it generated diversity on the landscape level and supported the development of ecosystems and species which we today like to protect. Most of the nutrient-poor grassland and shrub ecosystems owe their existence to the grazing of livestock or the necessity to feed them. Thermophilous plant and animal species found new habitats on grazing land, including forests. This book summarizes the results of scientific investigations on the influence of largescale pasturing on nature, conducted in Germany, Sweden, Ukraine and Georgia. The basic thought is: if livestock pasturing has contributed to generate the values of the kind of nature and landscapes which we today strive to protect, why not use it as a management tool? Of course, some modern forms of livestock keeping are obviously unsuitable to meet conservation targets. Today livestock is often kept in stables and if not is allowed to graze on small fenced paddocks only, which are normally fertilized, hosting only a poor level of biodiversity. But merging modern and historical techniques might result into a strategy well suited for landscape management. The validity of such models depends on the costs, for the farmer and for society, compared to other alternatives. Only if economical analyses back up such perspectives they will be realized on ground. The scientific and technical findings of this book are the result of the co-operation of many people. Editors and authors especially like to thank: Karl-Friedrich Abe, Kaltensundheim; Aribert Bach, Kaltensundheim; Matthias Dehling, Marburg; Sandro Didebulidze, Tbilisi; Angelika Fuß, Marburg; Helena Lager, Kalmar; Giorgi Nakhutsrishvili, Tbilisi; Ewald Sauer, Gersfeld; Beate Schütze, Berlin; Valentyn Stetsiuk, Lviv; Karl Stumpf, Ehrenberg; Josif Tsaryk, Lviv; Tengiz Urushadze, Tbilisi. We are also very grateful to the German Federal Ministry for Education and Research (BMBF), the Stifterverband für die Deutsche Wissenschaft, Essen, the Heidehof Stiftung, Stuttgart and the Stiftung für Naturschutz Thüringen, Erfurt, for having funded the research presented in this book. Finally we thank Christian Witschel and Armin Stasch, Springer Publ., for the careful preparation of this publication as well as L. Raey for the perfect translation into English.

This work focuses on fast approaches for image retrieval and classification by employing simple f... more This work focuses on fast approaches for image retrieval and classification by employing simple features to build image signatures. For this purpose a neural model for soft classification and automatic image annotation is proposed. The salient aspects of this solution are: a) the employment of a Radial Basis Function Network built on top of an image retrieval distance metric b) a soft learning strategy for annotation handling. Experiments have been conducted on a subset of the Corel image dataset for evaluation and comparative analysis.

Proceedings of the International Conference on Computer Vision Theory and Applications, 2011

Proceedings of the Second International Conference on Computer Vision Theory and Applications, 2007

Canadian Journal of Remote Sensing, 1999

ABSTRACT Ce papier propose une étude expérimentale pour analyser en profondeur comment deux techn... more ABSTRACT Ce papier propose une étude expérimentale pour analyser en profondeur comment deux techniques de classification non-conventionnelles, entre les plus couramment utilisées, basées sur les ensembles flous et sur les réseaux artificiels de neurones, peuvent contribuer à déterminer l'appartenance partielle aux classes de couverture du sol. Deux expériences ont été conduites pour achever cet objectif. Dans le premier on utilise des images artificielles simulées qui contiennent des pixels purs et des pixels mixes dont on connaît parfaitement la géometrie et la radiométrie (position et distribution des couvertures du sol au niveau de souspixel pour chaque pixel, comme ensemble complet de vérité-terrain). Dans deuxième expérience on examine une image satellitaire de la lagune de Venise (Italie) qui est caractérisée par un haut degré de complexité car les eaux et les wetland se mélangent les uns dans les autres, dessinant une composition emmelée et toujours changeante. La précision des résultats des deux techniques de classification a été évaluée et comparée parmi des outils d'évaluation qui ont été définis et développés à fin d'étendre les estimateurs traditionnels, soit descriptifs soit analytiques, dans le domaine propre des classes caractérisées par les degrés d'appartenance partielle. Les mesures de précision regardent l'identification de la composante dominante et des compositions de la mixture, l'ordination par pourcentage des composantes de la mixture et l'estimation de leur étendue. Une comparaison a été aussi établie avec la technique basée sur le modèle linéaire de mixture pour évaluer si les deux techniques non-conventionelles offrent être une alternative valide.

IFMBE Proceedings, 2009

ABSTRACT Aim of this work is to experimentally investigate the potential of a novel technique for... more ABSTRACT Aim of this work is to experimentally investigate the potential of a novel technique for CR image restoration which make use of gradient descent algorithm to minimize a local error function derived from the conventional global constrained error measure adopted within regularization approaches. Results of preliminary experiments show that the proposed restoration algorithm is promising for medical imaging restoration and could be useful in limiting x-ray dose absorbed by patients.

Analysis of Multi-Temporal Remote Sensing Images, 2002

Title: EXPLOITING SPATIAL AND TEMPORAL INFORMATION FOR EXTRACTING BURNED AREAS FROM TIME SERIES O... more Title: EXPLOITING SPATIAL AND TEMPORAL INFORMATION FOR EXTRACTING BURNED AREAS FROM TIME SERIES OF SPOT-VGT DATA. ... Milan, Italy M. MAGGI Remote Sensing Department., CNR, Milan, Italy E. BINAGHI Istituto per le Tecnologie Informatiche Multimediali ...

Communications in Computer and Information Science, 2007

Abstract. This work aims at defining a new method for matching correspondences in stereoscopic im... more Abstract. This work aims at defining a new method for matching correspondences in stereoscopic image analysis. The salient aspects of the method are -an explicit representation of occlusions driving the overall matching process and the use of neural adaptive technique in disparity ...

Lecture Notes in Computer Science

Frontiers of Remote Sensing Information Processing, 2003

CHAPTER 17 APPLICATION OF MULTIRESOLUTION REMOTE SENSING IMAGE ANALYSIS AND NEURAL TECHNIQUES TO ... more CHAPTER 17 APPLICATION OF MULTIRESOLUTION REMOTE SENSING IMAGE ANALYSIS AND NEURAL TECHNIQUES TO POWER LINES SURVEILLANCE Elisabetta Binaghi, Ignazio Gallo*. Monica Pepe* Dep. of Information and Communication Science, University ...

Image and Signal Processing for Remote Sensing VIII, 2003

ABSTRACT Contextual classification methods, which require the extraction of complex spatial infor... more ABSTRACT Contextual classification methods, which require the extraction of complex spatial information over a range of scales, from fine details in local areas to large features that extend across the image, are necessary in many remote sensing image classification studies. This work presents a supervised adaptive object recognition model which integrates scale-space filtering techniques for feature extraction within a neural classification procedure based on multilayer perceptron (MLP). The salient aspect of the model is the integration within the back-propagation learning task of the search of the most adequate filter parameters. The experimental evaluation of the method has been conducted coping with object recognition in high-resolution remote sensing imagery. To investigate whether the strategy can be considered an alternative to conventional procedures the results were compared with those obtained by a well known contextual classification scheme.

International journal for numerical methods in biomedical engineering, 2013

Accurate and efficient segmentation of the whole brain in magnetic resonance (MR) images is a key... more Accurate and efficient segmentation of the whole brain in magnetic resonance (MR) images is a key task in many neuroscience and medical studies either because the whole brain is the final anatomical structure of interest or because the automatic extraction facilitates further analysis. The problem of segmenting brain MRI images has been extensively addressed by many researchers. Despite the relevant achievements obtained, automated segmentation of brain MRI imagery is still a challenging problem whose solution has to cope with critical aspects such as anatomical variability and pathological deformation. In the present paper, we describe and experimentally evaluate a method for segmenting brain from MRI images basing on two-dimensional graph searching principles for border detection. The segmentation of the whole brain over the entire volume is accomplished slice by slice, automatically detecting frames including eyes. The method is fully automatic and easily reproducible by computin...

Image and Signal Processing for Remote Sensing XII, 2006

In computer vision, stereoscopic image analysis is a well-known technique capable of extracting t... more In computer vision, stereoscopic image analysis is a well-known technique capable of extracting the third (vertical) dimension. Starting from this knowledge, the Remote Sensing (RS) community has spent increasing efforts on the exploitation of Ikonos one-meter resolution stereo ...

Image Processing, Signal Processing, and Synthetic Aperture Radar for Remote Sensing, 1997

ABSTRACT In this study we propose the application of a fuzzy hybrid methodology for the classific... more ABSTRACT In this study we propose the application of a fuzzy hybrid methodology for the classification of wetlands in the Venice lagoon: one of the most delicate examples of these types of ecosystems in the world. The identification of wetlands in these transitional areas is not a trivial task, since they are characterized by mixed signatures, depending on the amount of water, bare soil and vegetation components mainly present in the ground pixel. On the other hand, the importance of the maintaining of wetland extents by the use of remote sensing data justifies new efforts in order to increase result reliability, overtaking those obtained by traditional classification techniques. In this work, a fuzzy hybrid methodology has been applied in a specific area of the Venice lagoon, by using Landsat Thematic Mapper images and a set of color aerial photographs, at a higher geometric resolution, taken simultaneously with the satellite images classification results have been judged by experts a reliable basis for further multisource data analyses and accurate mapping procedure.

Image and Signal Processing for Remote Sensing IX, 2004

In this paper, we propose a method able to fuse spectral information with spatial contextual info... more In this paper, we propose a method able to fuse spectral information with spatial contextual information in order to solve "operationally" classification problem. The salient aspect of the method is the integration of heterogeneous data within a Multi-Layer Perceptron model. Spatial and ...

Image and Signal Processing for Remote Sensing X, 2004

Hyperspectral imaging is becoming an important analytical tool for generating land-use map. High ... more Hyperspectral imaging is becoming an important analytical tool for generating land-use map. High dimensionality in hyperspectral remote sensing data, on one hand, provides us with more potential discrimination power for classification tasks. On the other hand, the classification performance improves up to a limited point as additional features are added, and then deteriorates due to the limited number of training

SPIE Proceedings, 1998

ABSTRACT This paper reports on an experimental study designed for the in-depth investigation of h... more ABSTRACT This paper reports on an experimental study designed for the in-depth investigation of how a supervised neuro-fuzzy classifier evaluates partial membership in land cover classes. The system is based on the Fuzzy Multilayer Perceptron model proposed by Pal and Mitra to which modifications in distance measures adopted for computing gradual membership to fuzzy class are introduced. During the training phase supervised learning is used to assign output class membership to pure training vectors (full membership to one land cover class); the model supports a procedure to automatically compute fuzzy output membership values for mixed training pixels. The classifier has been evaluated by conducting two experiments. The first employed simulated tests images which include pure and mixed pixels of known geometry and radiometry. The second experiment was conducted on a highly complex real scene of the Venice lagoon (Italy) where water and wetland merge into one another, at sub-pixel level. Accuracy of the results produced by the classifier was evaluated and compared using evaluation tools specifically defined and implemented to extend conventional descriptive and analytical statistical estimators to the case of multi-membership in classes. Results obtained demonstrated in the specific context of mixed pixels that the classification benefits from the integration of neural and fuzzy techniques.

SPIE Proceedings, 2001

The aim of the work is to propose a methodology for spatial/spectral analysis of urban patterns u... more The aim of the work is to propose a methodology for spatial/spectral analysis of urban patterns using neural network. To address the problem of spectral ambiguity and spatial complexity related to built-up patterns a two-stage classification procedure based on Multi-Layer Perceptron, ...

IEEE International Geoscience and Remote Sensing Symposium

The larger availability of high resolution remotely sensed data, provided by novel aircraft and s... more The larger availability of high resolution remotely sensed data, provided by novel aircraft and space sensors, offers new perspective to image processing techniques, but it introduces also the need for operational classification tools in order to completely exploit the potentialities of these data In many applicative contexts, in particular for technological network surveillance tasks, which involve specific requirements, such as

Communications in Computer and Information Science, 2011

Today we know that billions of products carry the 1-D bar codes, and with the increasing availabi... more Today we know that billions of products carry the 1-D bar codes, and with the increasing availability of camera phones, many applications that take advantage of immediate identification of the barcode are possible. The existing open-source libraries for 1-D barcodes recognition are not able to recognize the codes from images acquired using simple devices without autofocus or macro function. In this article we present an improvement of an existing algorithm for recognizing 1-D barcodes using camera phones ...