Contrast and lustre:a model that accounts for eleven different forms of contrast discrimination in binocular vision

Our goal here is a more complete understanding of how information about luminance contrast is encoded and used by the binocular visual system. In two-interval forced-choice experiments we assessed observers' ability to discriminate changes in contrast that could be an increase or decrease of contrast in one or both eyes, or an increase in one eye coupled with a decrease in the other (termed IncDec). The base or pedestal contrasts were either in-phase or out-of-phase in the two eyes. The opposed changes in the IncDec condition did not cancel each other out, implying that along with binocular summation, information is also available from mechanisms that do not sum the two eyes' inputs. These might be monocular mechanisms. With a binocular pedestal, monocular increments of contrast were much easier to see than monocular decrements. These findings suggest that there are separate binocular (B) and monocular (L,R) channels, but only the largest of the three responses, max(L,B,R), is available to perception and decision. Results from contrast discrimination and contrast matching tasks were described very accurately by this model. Stimuli, data, and model responses can all be visualized in a common binocular contrast space, allowing a more direct comparison between models and data. Some results with out-of-phase pedestals were not accounted for by the max model of contrast coding, but were well explained by an extended model in which gratings of opposite polarity create the sensation of lustre. Observers can discriminate changes in lustre alongside changes in contrast.

The domiciliary support in the vision of the informal care provider

The home support services are a social response in order to improve the quality of life directed predominantly for the elderly and for people with varying degrees of disability and dependence. Examples of those services are hygiene and personal comfort, medication, housekeeping and cleaning, preparation and monitoring of the meals; the dressing, etc. It is necessary to make society aware of the importance of these services to all those who need them. The general objective was to understand the most important relationships among informal caregivers, those who are care and home support services providers. Material and Methods. Data were collected through a questionnaire, using the various dimensions of the construct Quality SERVPERF model of service that matches the 22 items of SERVQUAL model. The various items used to assess the perception of care individuals and informal caregivers about the quality of home care services. 82 individuals participated providers of informal care, to receive home support services, and exclusion criteria, the fact of having a diagnosed psychiatric illness or psychological factors that prevent them from responding. The analysis was performed with SPSS and SEM-PLS for the estimation of the proposed structural model. Written consent was obtained, free and clear of each subject. Results and Conclusions. The results showed that the relationships with healthcare professionals are the most important positive effects on satisfaction. This research emphasizes the need to work closely with health professionals to improve the relationship between technicians and patients. Although current constructs appear to explain much of the satisfaction, it is recommended that the future researches exploit new variables, to get a better understanding of the effects of public health policies on the quality of life of these patients.

Preliminary report, Student Achievement and Vision Education (SAVE) proviso 55.5

During the 117th General Assembly of South Carolina, the Commission for Minority Affairs introduced the Student Achievement and Vision Education (SAVE) Proviso. The Proviso was so named to emphasize the importance of addressing student achievement by closing the gap that exists between majority and minority student performance and visioning students toward educational success through the implementation of the Education and Economic Development Act. This report documents the progress to date on the study; the impact of budget cuts on the CMA and complying agencies; the CMA's ability to complete the comprehensive study document using most current information; and the need for further study beyond February 2009.

Cloud Base Height Measurement System Based on Stereo Vision with Automatic Calibration

Clouds are important in weather prediction, climate studies and aviation safety. Important parameters include cloud height, type and cover percentage. In this paper, the recent improvements in the development of a low-cost cloud height measurement setup are described. It is based on stereo vision with consumer digital cameras. The cameras positioning is calibrated using the position of stars in the night sky. An experimental uncertainty analysis of the calibration parameters is performed. Cloud height measurement results are presented and compared with LIDAR measurements.

City & Spectacle: A Vision of Lisbon Before the 1755 Great Earthquake

City & Spectacle: a vision of pre-earthquake Lisbon consists of a virtual recrea on of the city of Lis- bon on the eve of the great earthquake of 1 November 1755, giving shape to a laboratory model for research into the city’s history. As its star ng point the project has the virtual recrea on of one the most emblema c of spaces from 18th century Lisbon, the Royal Opera House, which disappeared during the 1755 earthquake. The recrea on of the Opera House was developed in the scope of the commemora- ons of the 250th anniversary of the 1755 catastrophe as an a empt to restore this space of the highest ar s c quality to memory and to return it to the inventory of the Portuguese heritage of architectural history.1 Using Second Life® technology it was possible to put forward a model of both the struc- ture and interiors of the Opera House as well as its anima on combined with a small piece of the opera presented at the inaugura on of the building in April 1755. The public presenta on of this virtual model at the conference 1755: Catástrofe, memória e arte (1755: catastrophe, memory and art), which took place at the Centro de Estudos Compara- stas, Universidade de Lisboa, led to a debate on the study and cri cal analysis of documentary sources and their selec on and applica on on recrea ons using virtual world technology. It also emphasized the need to extend the research on pre-earthquake Lisbon.

Experiences from the course “Pedagogical Intervention in Preschool Education”: the vision from the faculty trainers, preschool teachers and students

As part of the educational formation of students from II level of the Associate dregree, from the Pedagogy major with an emphasis on preschool teaching from Universidad Nacional. There is a course named “Pedagogical Intervention in Early Childhood Education” which carries out the process of the intensive practicum. In this article you will find a review of the program’s objetives, experiences and challenges, taking the experiences from the academic team, who have guided this process over the past two years, and the point of views from students and preschool teachers.

EL USO POLITICO DEL TERRITORIO. CONSIDERACIONES A PARTIR DE UNA VISION DEL TERCER MUNDO

Análisis evaluativo de diversos enfoques geográficos sobre el espacio, su revelación con el Estado, entendido en su binomio poder y dominación. Se revisa la concepción de un poder unidimensional y la producción de espacio; así como las versiones del poder multidimensional, consumo del espacio y territorialidad. La concepción del espacio como producto-reflejo de la sociedad, se critica a la luz de concepción materialista del espacio. A nivel histórico, se estudian las estrategias y conflictos resultantes de la conformación de nuevos territorios y las limitaciones de acción del Estado frente a las decisiones locacionales de las grandes corporaciones multinacionales. Se fortalecen segmentos del Estado nacional, pero, a la vez, este pierde poder de decisiones ante las fuerzas internacionales y, principalmente frente a los problemas y tenciones internas. La autora sugiere diversos temas de investigación necesarios de cubrir urgentemente, tales como la relación territorio y espacio; naturaleza de los movimientos sociales de la base territorial; naturaleza del Estado contemporáneo y las relaciones ante los planes económicos y políticos y, finalmente, los limites de intervención del Estado y los problemas de legitimidad del poder. SUMMARY This is evaluative analysis of different geographic focuses concerning space-state relationships, taking into account a power and domination binomial. The concept of a unidimensional power and space production is revised; as well as versions of multidimensional power, space consumption, and territorial relationships. The space concept is taken into account as a product-reflection of society and criticized from the viewpoint of a materialistic viewpoint, strategies and conflicts are studied as the results of the confirmation of the new territories the large multinational corporations. Segments of the national state are stringency but, at the same time, the state loses its decision making powers in reference to international forces and principally in reference to problems and internal tensions. The author suggests several necessary and urgent investigative themes, such as territorial and space relationships, the nature of the social movements encountered in the territorial base, the nature of the contemporary state and of the its relationships in accordance with economic and political plants and finally, the intervention limits of the state and the problems of power legitimacy RESUME A partir d’une vision géographique, on présente et analyse les thèmes suivants: l’espace, la relation celui-ci avec l’Etat, entendu comme un bionome pouvoir et domination. On revise les concepts de pouvoir unidimensionnel et de production d’espace; de pouvoir multidimensionnel, consommation et territoriale. Le concept d’espace comme produit-réflexe de la société, est critiqué en se basant sur la conception matérialiste de l’espace. Au niveau historique, on étudie les stratégies et les conflicts qui résultent de la conformation de nouveaux territoires. On étudie aussi les limitations de l’action de l’Etat en face des décisions d’ubiquation des grandes corporations multinationales. En même temps que se fortifié certaines parties de l’Etat national, il y a une diminution de son pouvoir de décision devant des forces internationales et surtout en face de problèmes et de tensions internes.L’auteur suggère plusieurs thèmes d’investigation urgents, comme : la relation entre territoire et espace; nature des mouvements sociaux à base territoriale; nature de l’Etat contemporain et ses relations avec les plan économiques et politiques et enfin : les limites de l’intervention de l’Etat et les problèmes de légitimité du pouvoir. 

Scene Mapping and Understanding by Robotic Vision

The first mechanical Automaton concept was found in a Chinese text written in the 3rd century BC, while Computer Vision was born in the late 1960s. Therefore, visual perception applied to machines (i.e. the Machine Vision) is a young and exciting alliance. When robots came in, the new field of Robotic Vision was born, and these terms began to be erroneously interchanged. In short, we can say that Machine Vision is an engineering domain, which concern the industrial use of Vision. The Robotic Vision, instead, is a research field that tries to incorporate robotics aspects in computer vision algorithms. Visual Servoing, for example, is one of the problems that cannot be solved by computer vision only. Accordingly, a large part of this work deals with boosting popular Computer Vision techniques by exploiting robotics: e.g. the use of kinematics to localize a vision sensor, mounted as the robot end-effector. The remainder of this work is dedicated to the counterparty, i.e. the use of computer vision to solve real robotic problems like grasping objects or navigate avoiding obstacles. Will be presented a brief survey about mapping data structures most widely used in robotics along with SkiMap, a novel sparse data structure created both for robotic mapping and as a general purpose 3D spatial index. Thus, several approaches to implement Object Detection and Manipulation, by exploiting the aforementioned mapping strategies, will be proposed, along with a completely new Machine Teaching facility in order to simply the training procedure of modern Deep Learning networks.

Classificazione di Radiografie Toraciche per la Diagnosi del COVID-19 con Reti Convoluzionali e Vision Transformer

Negli ultimi due anni, per via della pandemia generata dal virus Covid19, la vita in ogni angolo del nostro pianeta è drasticamente cambiata. Ad oggi, nel mondo, sono oltre duecentoventi milioni le persone che hanno contratto questo virus e sono quasi cinque milioni le persone decedute. In alcuni periodi si è arrivati ad avere anche un milione di nuovi contagiati al giorno e mediamente, negli ultimi sei mesi, questo dato è stato di più di mezzo milione al giorno. Gli ospedali, soprattutto nei paesi meno sviluppati, hanno subito un grande stress e molte volte hanno avuto una carenza di risorse per fronteggiare questa grave pandemia. Per questo motivo ogni ricerca in questo campo diventa estremamente importante, soprattutto quelle che, con l'ausilio dell'intelligenza artificiale, riescono a dare supporto ai medici. Queste tecnologie una volta sviluppate e approvate possono essere diffuse a costi molto bassi e accessibili a tutti. In questo elaborato sono stati sperimentati e valutati due diversi approcci alla diagnosi del Covid-19 a partire dalle radiografie toraciche dei pazienti: il primo metodo si basa sul transfer learning di una rete convoluzionale inizialmente pensata per la classificazione di immagini. Il secondo approccio utilizza i Vision Transformer (ViT), un'architettura ampiamente diffusa nel campo del Natural Language Processing adattata ai task di Visione Artificiale. La prima soluzione ha ottenuto un’accuratezza di 0.85 mentre la seconda di 0.92, questi risultati, soprattutto il secondo, sono molto incoraggianti soprattutto vista la minima quantità di dati di training necessaria.

Previsione del Successo di Prodotti di Moda Prima della Commercializzazione: un Nuovo Dataset e Modello di Vision-Language Transformer

A differenza di quanto avviene nel commercio tradizionale, in quello online il cliente non ha la possibilità di toccare con mano o provare il prodotto. La decisione di acquisto viene maturata in base ai dati messi a disposizione dal venditore attraverso titolo, descrizioni, immagini e alle recensioni di clienti precedenti. É quindi possibile prevedere quanto un prodotto venderà sulla base di queste informazioni. La maggior parte delle soluzioni attualmente presenti in letteratura effettua previsioni basandosi sulle recensioni, oppure analizzando il linguaggio usato nelle descrizioni per capire come questo influenzi le vendite. Le recensioni, tuttavia, non sono informazioni note ai venditori prima della commercializzazione del prodotto; usando solo dati testuali, inoltre, si tralascia l’influenza delle immagini. L'obiettivo di questa tesi è usare modelli di machine learning per prevedere il successo di vendita di un prodotto a partire dalle informazioni disponibili al venditore prima della commercializzazione. Si fa questo introducendo un modello cross-modale basato su Vision-Language Transformer in grado di effettuare classificazione. Un modello di questo tipo può aiutare i venditori a massimizzare il successo di vendita dei prodotti. A causa della mancanza, in letteratura, di dataset contenenti informazioni relative a prodotti venduti online che includono l’indicazione del successo di vendita, il lavoro svolto comprende la realizzazione di un dataset adatto a testare la soluzione sviluppata. Il dataset contiene un elenco di 78300 prodotti di Moda venduti su Amazon, per ognuno dei quali vengono riportate le principali informazioni messe a disposizione dal venditore e una misura di successo sul mercato. Questa viene ricavata a partire dal gradimento espresso dagli acquirenti e dal posizionamento del prodotto in una graduatoria basata sul numero di esemplari venduti.

End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning

L'image captioning è un task di machine learning che consiste nella generazione di una didascalia, o caption, che descriva le caratteristiche di un'immagine data in input. Questo può essere applicato, ad esempio, per descrivere in dettaglio i prodotti in vendita su un sito di e-commerce, migliorando l'accessibilità del sito web e permettendo un acquisto più consapevole ai clienti con difficoltà visive. La generazione di descrizioni accurate per gli articoli di moda online è importante non solo per migliorare le esperienze di acquisto dei clienti, ma anche per aumentare le vendite online. Oltre alla necessità di presentare correttamente gli attributi degli articoli, infatti, descrivere i propri prodotti con il giusto linguaggio può contribuire a catturare l'attenzione dei clienti. In questa tesi, ci poniamo l'obiettivo di sviluppare un sistema in grado di generare una caption che descriva in modo dettagliato l'immagine di un prodotto dell'industria della moda dato in input, sia esso un capo di vestiario o un qualche tipo di accessorio. A questo proposito, negli ultimi anni molti studi hanno proposto soluzioni basate su reti convoluzionali e LSTM. In questo progetto proponiamo invece un'architettura encoder-decoder, che utilizza il modello Vision Transformer per la codifica delle immagini e GPT-2 per la generazione dei testi. Studiamo inoltre come tecniche di deep metric learning applicate in end-to-end durante l'addestramento influenzino le metriche e la qualità delle caption generate dal nostro modello.

Vision-Based Solutions for Human-Robot Collaboration in Industrial Workcells

Industrial robots are both versatile and high performant, enabling the flexible automation typical of the modern Smart Factories. For safety reasons, however, they must be relegated inside closed fences and/or virtual safety barriers, to keep them strictly separated from human operators. This can be a limitation in some scenarios in which it is useful to combine the human cognitive skill with the accuracy and repeatability of a robot, or simply to allow a safe coexistence in a shared workspace. Collaborative robots (cobots), on the other hand, are intrinsically limited in speed and power in order to share workspace and tasks with human operators, and feature the very intuitive hand guiding programming method. Cobots, however, cannot compete with industrial robots in terms of performance, and are thus useful only in a limited niche, where they can actually bring an improvement in productivity and/or in the quality of the work thanks to their synergy with human operators. The limitations of both the pure industrial and the collaborative paradigms can be overcome by combining industrial robots with artificial vision. In particular, vision can be exploited for a real-time adjustment of the pre-programmed task-based robot trajectory, by means of the visual tracking of dynamic obstacles (e.g. human operators). This strategy allows the robot to modify its motion only when necessary, thus maintain a high level of productivity but at the same time increasing its versatility. Other than that, vision offers the possibility of more intuitive programming paradigms for the industrial robots as well, such as the programming by demonstration paradigm. These possibilities offered by artificial vision enable, as a matter of fact, an efficacious and promising way of achieving human-robot collaboration, which has the advantage of overcoming the limitations of both the previous paradigms yet keeping their strengths.

Continual learning for computer vision applications

One of the most visionary goals of Artificial Intelligence is to create a system able to mimic and eventually surpass the intelligence observed in biological systems including, ambitiously, the one observed in humans. The main distinctive strength of humans is their ability to build a deep understanding of the world by learning continuously and drawing from their experiences. This ability, which is found in various degrees in all intelligent biological beings, allows them to adapt and properly react to changes by incrementally expanding and refining their knowledge. Arguably, achieving this ability is one of the main goals of Artificial Intelligence and a cornerstone towards the creation of intelligent artificial agents. Modern Deep Learning approaches allowed researchers and industries to achieve great advancements towards the resolution of many long-standing problems in areas like Computer Vision and Natural Language Processing. However, while this current age of renewed interest in AI allowed for the creation of extremely useful applications, a concerningly limited effort is being directed towards the design of systems able to learn continuously. The biggest problem that hinders an AI system from learning incrementally is the catastrophic forgetting phenomenon. This phenomenon, which was discovered in the 90s, naturally occurs in Deep Learning architectures where classic learning paradigms are applied when learning incrementally from a stream of experiences. This dissertation revolves around the Continual Learning field, a sub-field of Machine Learning research that has recently made a comeback following the renewed interest in Deep Learning approaches. This work will focus on a comprehensive view of continual learning by considering algorithmic, benchmarking, and applicative aspects of this field. This dissertation will also touch on community aspects such as the design and creation of research tools aimed at supporting Continual Learning research, and the theoretical and practical aspects concerning public competitions in this field.

Neurogeometry of stereo vision

This work aims to develop a neurogeometric model of stereo vision, based on cortical architectures involved in the problem of 3D perception and neural mechanisms generated by retinal disparities. First, we provide a sub-Riemannian geometry for stereo vision, inspired by the work on the stereo problem by Zucker (2006), and using sub-Riemannian tools introduced by Citti-Sarti (2006) for monocular vision. We present a mathematical interpretation of the neural mechanisms underlying the behavior of binocular cells, that integrate monocular inputs. The natural compatibility between stereo geometry and neurophysiological models shows that these binocular cells are sensitive to position and orientation. Therefore, we model their action in the space R3xS2 equipped with a sub-Riemannian metric. Integral curves of the sub-Riemannian structure model neural connectivity and can be related to the 3D analog of the psychophysical association fields for the 3D process of regular contour formation. Then, we identify 3D perceptual units in the visual scene: they emerge as a consequence of the random cortico-cortical connection of binocular cells. Considering an opportune stochastic version of the integral curves, we generate a family of kernels. These kernels represent the probability of interaction between binocular cells, and they are implemented as facilitation patterns to define the evolution in time of neural population activity at a point. This activity is usually modeled through a mean field equation: steady stable solutions lead to consider the associated eigenvalue problem. We show that three-dimensional perceptual units naturally arise from the discrete version of the eigenvalue problem associated to the integro-differential equation of the population activity.