Nello Balossino

Gait characterization using dynamic skeleton acquisition

Human gait is an important biometric feature for automatic people recognition. Biometric methodologies are generally intrusive and require the collaboration of the subject in order to perform accurate data acquisition. Gait, instead, can be captured at a distance and without collaboration. This makes it an unobtrusive method for recognizing people in video surveillance systems. In this paper we propose a method to characterize walking gait using three-dimensional skeleton information acquired by the Microsoft Kinect sensor. A set of static and dynamic features correlated to human gait are extracted by the estimated skeleton joint positions. Moreover, we proposed to describe joints positions in a coordinate reference system oriented according to the walking direction to better represents the movement of human body. Using unsupervised clustering over a set of 20 subjects we analyze the effectiveness of the selected features in discriminating people gaits. It turns out that a few dynamic parameters involving the movement of knees, elbows and head are good candidates for robust gait characterization.

Human Classification Using Gait Features

Gait exhibits several advantages with respect to other biometrics features: acquisition can be performed through cheap technology, at a distance and without people collaboration. In this paper we perform gait analysis using skeletal data provided by the Microsoft Kinect sensor. We defined a rich set of physical and behavioral features aiming at identifying the more relevant parameters for gait description. Using SVM we showed that a limited set of behavioral features related to the movements of head, elbows and knees is a very effective tool for gait characterization and people recognition. In particular, our experimental results shows that it is possible to achieve 96% classification accuracy when discriminating a group of 20 people.

Kinect-Based Gait Analysis for People Recognition Over Time.

Gait has recently attracted a great interest in the biometric field because, contrary to other classical biometric traits such as fingerprint, iris or retina, it allows to capture samples at a distance, through inexpensive and not intrusive technologies that do not need any subject’s collaboration. In spite of this advantage, such technique is still not widespread for human identification task, because it is considered not to exhibit the fundamental characteristic of being invariant in the lifetime of each individual. But is this assertion really true? In this paper we investigate if gait can be considered invariant over time for an individual, at least in a time interval of few years, by comparing gait samples of several subjects three years apart. We train a Support Vector Machine with gait samples of 10 subjects, then we employ it for recognizing the same subjects with gait samples collected three years later. In addition, we try to recognize the subjects carrying three different accessories: a shoulder bag, a backpack and a smartphone.

A New Stereo Algorithm Integrating Luminance, Gradient and Segmentation Informations in a Belief-Propagation Framework

The paper deals with the design and implementation of a stereo algorithm. Disparity map is formulated as a Markov Random Field with a new smoothness constraint depending not only on image derivatives, but also on segmentation results and gradient directions. With these constraints we force disparity continuity inside each segmented object, while its contours are well preserved. Moreover we have designed a modified version of Belief Propagation which gives the solution to the stereo matching problem: the optimization has remarkable improvements and especially with respect to message propagation, which is actually driven by segmentation and boundary knowledge. Preliminary results are presented both on synthetic and benchmark images to demonstrate the effectiveness of our method.

Acyclic belief propagation for stereo matching

Most of the works for solving early vision problems, such as stereo, rely on inference techniques and cyclic graphical models. Although Loopy Belief Propagation is one of the most interesting tools as it applies to that research field, loops are still a major challenge to face: the main problem arising with them is the introduction of approximation issues which could affect the accuracy of the final results. Therefore, breaking loops could be the winning strategy to overcome these problems. In this paper, we describe a way to consider an MRF grid as composed by a suitable set of singly connected graphs. Then, an acyclic propagation scheme, based on that set, is given accordingly. Experiments performed on different stereo pairs will prove that our approach is up to the current state-of-art and it spreads several new research issues for the future.

‘IXV-trajectory’ and ‘IXV-asset’: Virtual reality applications for the aerothermodynamics analysis of IXV

Design and engineering of space vehicles involve several different disciplines, each of which have specific research methodologies and software tools. Interaction among the physical analysis tools, as well as collaboration among teams, is a delicate and difficult subject of collaborative engineering research topics. This paper presents a solution based on a new technical and interaction design. We encourage the development of Virtual Reality 3D applications to interface the tools that perform the quantitative physical analysis of given space vehicles, as this approach improves productivity and communication effectiveness and brings consisting benefits to the engineering and design collaborative processes. As an evaluation of this method, we report the design and implementation of two Virtual Reality Applications specifically developed for the European Space Agencys space vehicle IXV. This evaluation showed that users found the Virtual Reality interface easy to use and likely to be useful in their own work. The benefits underlined by this method brought to the acquirement of this approach as the new future standard methodology in pre-launch phases of space vehicles.

Luce, immagini e visione

Un’immagine e la rappresentazione grafica di una scena tratta dalla realta, oppure di un fenomeno di qualsiasi natura, nonche del risultato di una modellazione o simulazione di un evento. Una sommaria classificazione delle immagini e la seguente: immagini reali: sono rilevabili direttamente dall’ambiente; un esempio e quello delle immagini derivanti da riprese video-fotografiche; immagini scientifiche: definiscono l’evoluzione della distribuzione spazio-temporale di grandezze fisiche, ad esempio la temperatura, la pressione, il potenziale elettromagnetico, il legame chimico, le radiazioni; immagini sintetiche: sono costituite dalla rappresentazione grafica di funzioni matematiche di piu variabili che modellano un ambiente o un soggetto, ma anche ne simulano il comportamento secondo leggi fisiche o di fantasia.

Introduzione all’immagine digitale

Tutte le immagini digitali sono il risultato di un processo di acquisizione che comprende sempre nelle sue diverse fasi un’operazione di campionamento e una di quantizzazione o conversione analogico digitale, come schematizzato in Figura 3.1. Nell’ambito della fotografia digitale e in quello della radiologia proiettiva, per esempio, il sensore utilizzato e in grado di misurare l’intensita di radiazione luminosa o ionizzante incidente e contestualmente effettua un campionamento il cui passo di discretizzazione dipende dalle dimensioni dei singoli rivelatori che compongono la sua matrice di acquisizione. Tutte le misure vengono poi convertite in dato numerico digitale e attribuite ai valori dei singoli pixel (picture element) dell’immagine. In altri ambiti della radiologia, il processo di formazione dell’immagine e piu complesso e coinvolge sofisticate elaborazioni matematiche, ma troveremo comunque una fase di campionamento e quantizzazione del segnale di origine che condizionera poi il risultato dell’immagine finale.

Rappresentazione digitale di segnali

Per controllare la temperatura in un ambiente, mantenendola entro limiti prefissati, e sufficiente paragonare la tensione proveniente dal sensore di temperatura con una tensione utilizzata come riferimento, comandando opportunamente il dispositivo preposto al riscaldamento; si tratta di un segnale analogico che varia con continuita.

Elaborazione di immagini

La principale caratteristica delle immagini digitali e la possibilita di sottoporle a elaborazione numerica: i pixel possiedono caratteristiche di colore e luminosita associate a numeri, il cui valore puo essere modificato secondo opportuni algoritmi di trasformazione; le caratteristiche dell’immagine finale saranno frutto delle trasformazioni applicate.