Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.

Collection and real-time analysis of images from aircraft to support civil protection operational activities

This report describes the realization of a system, in which an object detection model will be implemented, whose aim is to detect the presence of people in images. This system could be used for several applications: for example, it could be carried on board an aircraft or a drone. In this case, the system is designed in such a way that it can be mounted on light/medium weight helicopters, helping the operator to find people in emergency situations. In the first chapter the use of helicopters for civil protection is analysed and applications similar to this case study are listed. The second chapter describes the choice of the hardware devices that have been used to implement a prototype of a system to collect, analyse and display images. At first, the PC necessary to process the images was chosen, based on the characteristics of the algorithms that are necessary to run the analysis. In the further, a camera that could be compatible with the PC was selected. Finally, the battery pack was chosen taking into account the electrical consumption of the devices. The third chapter illustrates the algorithms used for image analysis. In the fourth, some of the requirements listed in the regulations that must be taken into account for carrying on board all the devices have been briefly analysed. In the fifth chapter the activity of design and modelling, with the CAD Solidworks, the devices and a prototype of a case that will house them is described. The sixth chapter discusses the additive manufacturing, since the case was printed exploiting this technology. In the seventh chapter, part of the tests that must be carried out on the equipment to certificate it have been analysed, and some simulations have been carried out. In the eighth chapter the results obtained once loaded the object detection model on a hardware for image analyses were showed. In the ninth chapter, conclusions and future applications were discussed.

Comparison of EEG signals from epilepsy patients with Bump modeling

Background: l’epilessia è una malattia cerebrale che colpisce oggigiorno circa l’1% della popolazione mondiale e causa, a chi ne soffre, convulsioni ricorrenti e improvvise che danneggiano la vita quotidiana del paziente. Le convulsioni sono degli eventi che bloccano istantaneamente la normale attività cerebrale; inoltre differiscono tra i pazienti e, perciò, non esiste un trattamento comune generalizzato. Solitamente, medici neurologi somministrano farmaci, e, in rari casi, l’epilessia è trattata con operazioni neurochirurgiche. Tuttavia, le operazioni hanno effetti positivi nel ridurre le crisi, ma raramente riescono a eliminarle del tutto. Negli ultimi anni, nel campo della ricerca scientifica è stato provato che il segnale EEG contiene informazioni utili per diagnosticare l'arrivo di un attacco epilettico. Inoltre, diversi algoritmi automatici sono stati sviluppati per rilevare automaticamente le crisi epilettiche. Scopo: lo scopo finale di questa ricerca è l'applicabilità e l'affidabilità di un dispositivo automatico portatile in grado di rilevare le convulsioni e utilizzabile come sistema di monitoraggio. L’analisi condotta in questo progetto, è eseguita con tecniche di misure classiche e avanzate, in modo tale da provare tecnicamente l’affidabilità di un tale sistema. La comparazione è stata eseguita sui segnali elettroencefalografici utilizzando due diversi sistemi di acquisizione EEG: il metodo standard utilizzato nelle cliniche e il nuovo dispositivo portatile. Metodi: è necessaria una solida validazione dei segnali EEG registrati con il nuovo dispositivo. I segnali saranno trattati con tecniche classiche e avanzate. Dopo le operazioni di pulizia e allineamento, verrà utilizzato un nuovo metodo di rappresentazione e confronto di segnali : Bump model. In questa tesi il metodo citato verrà ampiamente descritto, testato, validato e adattato alle esigenze del progetto. Questo modello è definito come un approccio economico per la mappatura spazio-frequenziale di wavelet; in particolare, saranno presenti solo gli eventi con un’alta quantità di energia. Risultati: il modello Bump è stato implementato come toolbox su MATLAB dallo sviluppatore F. Vialatte, e migliorato dall’Autore per l’utilizzo di registrazioni EEG da sistemi diversi. Il metodo è validato con segnali artificiali al fine di garantire l’affidabilità, inoltre, è utilizzato su segnali EEG processati e allineati, che contengono eventi epilettici. Questo serve per rilevare la somiglianza dei due sistemi di acquisizione. Conclusioni: i risultati visivi garantiscono la somiglianza tra i due sistemi, questa differenza la si può notare specialmente comparando i grafici di attività background EEG e quelli di artefatti o eventi epilettici. Bump model è uno strumento affidabile per questa applicazione, e potrebbe essere utilizzato anche per lavori futuri (ad esempio utilizzare il metodo di Sincronicità Eventi Stocas- tici SES) o differenti applicazioni, così come le informazioni estratte dai Bump model potrebbero servire come input per misure di sincronicità, dalle quali estrarre utili risultati.