Publications

Hidden Markov Models (HMM) have been widely used for action recognition, since they allow to easily model the temporal evolution of a single or a set of numeric features extracted from the data. The selection of the feature set and the related emission probability function are the key issues to be defined. In particular, if the training set is not sufficiently large, a manual or automatic feature selection and reduction is mandatory. In this paper we propose to model the emission probability function as a Mixture of Gaussian and the feature set is obtained from the projection histograms of the foreground mask. The projectionhistograms contain the number of moving pixel for each row and for each column of the frame and they provide sufficient information to infer the instantaneous posture of the person. Then, the HMM framework recovers the temporal evolution of the postures recognizing in such a manner the global action. The proposed method have been successfully tested on the UT-Tower and on the Weizmann Datasets.

This paper presents a method for comparing people trajectories for video surveillance applications, based on semi-directional statistics. In fact, the modelling of a trajectory as a sequence of angles, speeds and time lags, requires the use of a statistical tool capable to jointly consider periodic and linear variables. Our statistical method is compared with two state-of-the-art methods.

Achieving both localization and identication of people ina wide open area using only cameras can be a challengingtask, which requires cross-cutting requirements : high reso-lution for identication, whereas low resolution for having awide coverage of the localization. Consequently, this paperproposes the joint use of cameras (only devoted to local-ization) and RFID sensors (devoted to identication) withthe nal objective of detecting and localizing intruders. Toground the observations on a common coordinate system,a calibration procedure is dened. This procedure only de-mands a training phase with a single person moving in thescene holding a RFID tag. Although preliminary, the resultsdemonstrate that this calibration is sufficiently accurate tobe applied whenever dierent scenarios, where area of over-lap between the eld of view (FoV) of a camera and theField of sense" (FoS) of a (blind) sensor must be efficientlydetermined.

In this paper a system for illuminated manuscripts images analysis is presented. In particular the bag-of-keypoints strategy, commonly adopted for object recognition, image classification and scene recognition, is applied to the classification of automatically extracted miniatures. Pictures are characterized by SURF descriptors, and a classification procedure is performed, comparing the results of Naive Bayes and histogram intersection distance measures.

The term mobile is now added to most of computer based systems as synonymous of several different concepts, ranging on ubiquitousness, wireless connection, portability, and so on. In a similar manner, also the name mobile video surveillance is spreading, even though it is often misinterpreted with just limited views of it, such as front-end mobile monitoring, wireless video streaming, moving cameras, distributed systems. This chapter presents an overview of mobile video surveillance systems, focusing in particular on architectural aspects (sensors, functional units and sink modules). A short survey of the state of the art is presented. The chapter will also tackle some problems of video streaming and video tracking specifically designed and optimized for mobile video surveillance systems, giving an idea of the best results that can be achieved in these two foundation layers. © 2010 Springer-Verlag.

This paper presents two automated methods for the segmentation ofimmunohistochemical tissue images that overcome the limitations of themanual approach aswell as of the existing computerized techniques. The first independent method, based on unsupervised color clustering, recognizes automatically the target cancerous areas in the specimen and disregards the stroma; the second method, based on colors separation and morphological processing, exploits automated segmentation of the nuclear membranes of the cancerous cells. Extensive experimental results on real tissue images demonstrate the accuracy of our techniques compared to manual segmentations; additional experiments show that our techniques are more effective in immunohistochemical images than popular approaches based on supervised learning or active contours. The proposed procedure can be exploited for any applications that require tissues and cells exploration and to perform reliable and standardized measures of the activity of specific proteins involved in multi-factorial genetic pathologies.

In questo articolo si parla delle nuove frontiere di visione artificiale nella videosorveglianza di persone in ambienti pubblici e privati ed in particolare di analisi comportamentale. Sono poi presentate alcuni progetti in corso presso l’ImageLab di Modena

We propose a new efficient approach for neighborhood exploration, optimized with decision tables and decision trees, suitable for local algorithms in image processing. In this work, it is employed to speed up two widely used thinning techniques. The performance gain is shown over a large freely available dataset of scanned document images.

Gene regulation is one of the most important processes in the molecular biology, in the last years the microRNA molecule, one of the non-coding RNAs involved in the process, has been the focus of attention for several studies. The computational research on this area has gained a notable importance, considering the low amount of experimental information available and the lack of understanding of the microRNA binding mechanism. This article deals with the microRNA-target prediction and presents an innovative method for it. First it generates a set of promising binding sites for a given microRNA using a Genetic Algorithm, at the same time a set of target genes is selected based on the biological process under study. Secondly the set of promising binding sites is mapped into the selected set of target genes, in order to provide real binding sites and finally the resulting targets are filtered according to a biological or structural property. The objectives are to provide a flexible method that is capable of incorporating easily new knowledge, is independent of availability of the experimental information and is able to give hints on the research towards new characteristics among the microRNA binding sites such as motifs. The results present some of this novel properties and present a comparison with the most frequently used methods in the field. © 2010 IEEE.