Quantum of Vision

Visual inputs to artificial and biological visual systems are often quantized: cameras accumulate photons from the visual world, and the brain receives action potentials from visual sensory neurons. Collecting more information quanta leads to a longer acquisition time and better performance. In many visual tasks, collecting a small number of quanta is sufficient to solve the task well. The ability to determine the right number of quanta is pivotal in situations where visual information is costly to obtain, such as photon-starved or time-critical environments. In these situations, conventional vision systems that always collect a fixed and large amount of information are infeasible. I develop a framework that judiciously determines the number of information quanta to observe based on the cost of observation and the requirement for accuracy. The framework implements the optimal speed versus accuracy tradeoff when two assumptions are met, namely that the task is fully specified probabilistically and constant over time. I also extend the framework to address scenarios that violate the assumptions. I deploy the framework to three recognition tasks: visual search (where both assumptions are satisfied), scotopic visual recognition (where the model is not specified), and visual discrimination with unknown stimulus onset (where the model is dynamic over time). Scotopic classification experiments suggest that the framework leads to dramatic improvement in photon-efficiency compared to conventional computer vision algorithms. Human psychophysics experiments confirmed that the framework provides a parsimonious and versatile explanation for human behavior under time pressure in both static and dynamic environments.

Improving surgery operations by means of cloud systems and distributed user interfaces

Surgical interventions are usually performed in an operation room; however, access to the information by the medical team members during the intervention is limited. While in conversations with the medical staff, we observed that they attach significant importance to the improvement of the information and communication direct access by queries during the process in real time. It is due to the fact that the procedure is rather slow and there is lack of interaction with the systems in the operation room. These systems can be integrated on the Cloud adding new functionalities to the existing systems the medical expedients are processed. Therefore, such a communication system needs to be built upon the information and interaction access specifically designed and developed to aid the medical specialists. Copyright 2014 ACM.

Concepts and methods for efficient decentralized learning in federated settings

Deep Neural Networks (DNNs) have revolutionized a wide range of applications beyond traditional machine learning and artificial intelligence fields, e.g., computer vision, healthcare, natural language processing and others. At the same time, edge devices have become central in our society, generating an unprecedented amount of data which could be used to train data-hungry models such as DNNs. However, the potentially sensitive or confidential nature of gathered data poses privacy concerns when storing and processing them in centralized locations. To this purpose, decentralized learning decouples model training from the need of directly accessing raw data, by alternating on-device training and periodic communications. The ability of distilling knowledge from decentralized data, however, comes at the cost of facing more challenging learning settings, such as coping with heterogeneous hardware and network connectivity, statistical diversity of data, and ensuring verifiable privacy guarantees. This Thesis proposes an extensive overview of decentralized learning literature, including a novel taxonomy and a detailed description of the most relevant system-level contributions in the related literature for privacy, communication efficiency, data and system heterogeneity, and poisoning defense. Next, this Thesis presents the design of an original solution to tackle communication efficiency and system heterogeneity, and empirically evaluates it on federated settings. For communication efficiency, an original method, specifically designed for Convolutional Neural Networks, is also described and evaluated against the state-of-the-art. Furthermore, this Thesis provides an in-depth review of recently proposed methods to tackle the performance degradation introduced by data heterogeneity, followed by empirical evaluations on challenging data distributions, highlighting strengths and possible weaknesses of the considered solutions. Finally, this Thesis presents a novel perspective on the usage of Knowledge Distillation as a mean for optimizing decentralized learning systems in settings characterized by data heterogeneity or system heterogeneity. Our vision on relevant future research directions close the manuscript.

Computational methods applied to undeciphered scripts from the Aegean and Cyprus: Linear A and Cypro-Minoan

The study of ancient, undeciphered scripts presents unique challenges, that depend both on the nature of the problem and on the peculiarities of each writing system. In this thesis, I present two computational approaches that are tailored to two different tasks and writing systems. The first of these methods is aimed at the decipherment of the Linear A afraction signs, in order to discover their numerical values. This is achieved with a combination of constraint programming, ad-hoc metrics and paleographic considerations. The second main contribution of this thesis regards the creation of an unsupervised deep learning model which uses drawings of signs from ancient writing system to learn to distinguish different graphemes in the vector space. This system, which is based on techniques used in the field of computer vision, is adapted to the study of ancient writing systems by incorporating information about sequences in the model, mirroring what is often done in natural language processing. In order to develop this model, the Cypriot Greek Syllabary is used as a target, since this is a deciphered writing system. Finally, this unsupervised model is adapted to the undeciphered Cypro-Minoan and it is used to answer open questions about this script. In particular, by reconstructing multiple allographs that are not agreed upon by paleographers, it supports the idea that Cypro-Minoan is a single script and not a collection of three script like it was proposed in the literature. These results on two different tasks shows that computational methods can be applied to undeciphered scripts, despite the relatively low amount of available data, paving the way for further advancement in paleography using these methods.

Data-driven and data-oriented methods for materials science and technologies

The discovery of new materials and their functions has always been a fundamental component of technological progress. Nowadays, the quest for new materials is stronger than ever: sustainability, medicine, robotics and electronics are all key assets which depend on the ability to create specifically tailored materials. However, designing materials with desired properties is a difficult task, and the complexity of the discipline makes it difficult to identify general criteria. While scientists developed a set of best practices (often based on experience and expertise), this is still a trial-and-error process. This becomes even more complex when dealing with advanced functional materials. Their properties depend on structural and morphological features, which in turn depend on fabrication procedures and environment, and subtle alterations leads to dramatically different results. Because of this, materials modeling and design is one of the most prolific research fields. Many techniques and instruments are continuously developed to enable new possibilities, both in the experimental and computational realms. Scientists strive to enforce cutting-edge technologies in order to make progress. However, the field is strongly affected by unorganized file management, proliferation of custom data formats and storage procedures, both in experimental and computational research. Results are difficult to find, interpret and re-use, and a huge amount of time is spent interpreting and re-organizing data. This also strongly limit the application of data-driven and machine learning techniques. This work introduces possible solutions to the problems described above. Specifically, it talks about developing features for specific classes of advanced materials and use them to train machine learning models and accelerate computational predictions for molecular compounds; developing method for organizing non homogeneous materials data; automate the process of using devices simulations to train machine learning models; dealing with scattered experimental data and use them to discover new patterns.

Analysis and development of interface components and procedures for the design and commissioning toolchains in automation systems

The objective of the thesis project, developed within the Line Control & Software Engineering team of G.D company, is to analyze and identify the appropriate tool to automate the HW configuration process using Beckhoff technologies by importing data from an ECAD tool. This would save a great deal of time, since the I/O topology created as part of the electrical planning is presently imported manually in the related SW project of the machine. Moreover, a manual import is more error-prone because of human mistake than an automatic configuration tool. First, an introduction about TwinCAT 3, EtherCAT and Automation Interface is provided; then, it is analyzed the official Beckhoff tool, XCAD Interface, and the requirements on the electrical planning to use it: the interface is realized by means of the AutomationML format. Finally, due to some limitations observed, the design and implementation of a company internal tool is performed. Tests and validation of the tool are performed on a sample production line of the company.

Machine learning and convolutional neural networks for melanomas identification

Il machine learning negli ultimi anni ha acquisito una crescente popolarità nell’ambito della ricerca scientifica e delle sue applicazioni. Lo scopo di questa tesi è stato quello di studiare il machine learning nei suoi aspetti generali e applicarlo a problemi di computer vision. La tesi ha affrontato le difficoltà del dover spiegare dal punto di vista teorico gli algoritmi alla base delle reti neurali convoluzionali e ha successivamente trattato due problemi concreti di riconoscimento immagini: il dataset MNIST (immagini di cifre scritte a mano) e un dataset che sarà chiamato ”MELANOMA dataset” (immagini di melanomi e nevi sani). Utilizzando le tecniche spiegate nella sezione teorica si sono riusciti ad ottenere risultati soddifacenti per entrambi i dataset ottenendo una precisione del 98% per il MNIST e del 76.8% per il MELANOMA dataset

Neural Radiance Fields for Relighting and View Synthesis

Neural scene representation and neural rendering are new computer vision techniques that enable the reconstruction and implicit representation of real 3D scenes from a set of 2D captured images, by fitting a deep neural network. The trained network can then be used to render novel views of the scene. A recent work in this field, Neural Radiance Fields (NeRF), presented a state-of-the-art approach, which uses a simple Multilayer Perceptron (MLP) to generate photo-realistic RGB images of a scene from arbitrary viewpoints. However, NeRF does not model any light interaction with the fitted scene; therefore, despite producing compelling results for the view synthesis task, it does not provide a solution for relighting. In this work, we propose a new architecture to enable relighting capabilities in NeRF-based representations and we introduce a new real-world dataset to train and evaluate such a model. Our method demonstrates the ability to perform realistic rendering of novel views under arbitrary lighting conditions.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.

Rastreamento automatico de trajetorias de jogadores de futebol por videogrametria : validação do metodo e analise dos resultados

Universidade Estadual de Campinas . Faculdade de Educação Física

On the k-restricted structure ratio in planar and outerplanar graphs

A planar k-restricted structure is a simple graph whose blocks are planar and each has at most k vertices. Planar k-restricted structures are used by approximation algorithms for Maximum Weight Planar Subgraph, which motivates this work. The planar k-restricted ratio is the infimum, over simple planar graphs H, of the ratio of the number of edges in a maximum k-restricted structure subgraph of H to the number edges of H. We prove that, as k tends to infinity, the planar k-restricted ratio tends to 1/2. The same result holds for the weighted version. Our results are based on analyzing the analogous ratios for outerplanar and weighted outerplanar graphs. Here both ratios tend to 1 as k goes to infinity, and we provide good estimates of the rates of convergence, showing that they differ in the weighted from the unweighted case.

Use of peripheral vision in the interception of moving targets

Use of peripheral vision to organize and reorganize an interceptive action was investigated in young adults. Temporal errors and kinematic variables were evaluated in the interception of a virtual moving target, in situations in which its initial velocity was kept unchanged or was unexpectedly decreased. Observation of target approach was made through continuous visual pursuit (focal vision) or keeping visual focus at the origin of the trajectory or at the contact spot (peripheral vision). Results showed that visual focus at the contact spot led to temporal errors similar to focal vision, although showing a distinct kinematic profile, while focus at the origin led to an impoverished performance

Measurement Function Design for Visual Tracking Applications

Extracting human postural information from video sequences has proved a difficult research question. The most successful approaches to date have been based on particle filtering, whereby the underlying probability distribution is approximated by a set of particles. The shape of the underlying observational probability distribution plays a significant role in determining the success, both accuracy and efficiency, of any visual tracker. In this paper we compare approaches used by other authors and present a cost path approach which is commonly used in image segmentation problems, however is currently not widely used in tracking applications.

Embedded Voxel Colouring

The reconstruction of a complex scene from multiple images is a fundamental problem in the field of computer vision. Volumetric methods have proven to be a strong alternative to traditional correspondence-based methods due to their flexible visibility models. In this paper we analyse existing methods for volumetric reconstruction and identify three key properties of voxel colouring algorithms: a water-tight surface model, a monotonic carving order, and causality. We present a new Voxel Colouring algorithm which embeds all reconstructions of a scene into a single output. While modelling exact visibility for arbitrary camera locations, Embedded Voxel Colouring removes the need for a priori threshold selection present in previous work. An efficient implementation is given along with results demonstrating the advantages of posteriori threshold selection.

Comparison of palmtop-computer-assisted brief cognitive-behavioral treatment to cognitive-behavioral treatment for panic disorder

In the present study, the authors sought to determine whether the efficiency and cost-effectiveness of cognitive-behavioral treatment (CBT) for panic disorder could be improved by adjunctive computer-assisted therapy. Eighteen participants who met Diagnostic and Statistical Manual of Mental Disorders (3rd ed., revised; American Psychiatric Association, 1987) criteria for panic disorder were randomly assigned to a 12-session CBT (CBT12) condition (D. H. Barlow & M. G. Craske, 1989) or to a 4-session computer-assisted CBT (CBT4-CA) condition. Palmtop computers, with a program developed to incorporate basic principles of CBT, were used by CBT4-CA clients whenever they felt anxious or wanted to practice the therapy techniques and were used by all participants as a momentary assessment tool. CBT4-CA clients carried the computer at all times and continued to use it for 8 weeks after termination of therapy. Analyses of clinically significant change showed superiority of CBT12 at posttest on some measures; however, there were no differences at follow-up.