Sistema de visão para percepção e navegação de um UAV Quadrotor

Mestrado em Engenharia Electrotécnica e de Computadores

Management Driven Hybrid Multicast Framework for Content Aware Networks

The need for better adaptation of networks to transported flows has led to research on new approaches such as content aware networks and network aware applications. In parallel, recent developments of multimedia and content oriented services and applications such as IPTV, video streaming, video on demand, and Internet TV reinforced interest in multicast technologies. IP multicast has not been widely deployed due to interdomain and QoS support problems; therefore, alternative solutions have been investigated. This article proposes a management driven hybrid multicast solution that is multi-domain and media oriented, and combines overlay multicast, IP multicast, and P2P. The architecture is developed in a content aware network and network aware application environment, based on light network virtualization. The multicast trees can be seen as parallel virtual content aware networks, spanning a single or multiple IP domains, customized to the type of content to be transported while fulfilling the quality of service requirements of the service provider.

NONIUS.TV na SMART TV LG PRO: Centric

A Smart TV é um equipamento novo e em evolução que incorpora um computador e acesso à Internet em ecrãs de grande qualidade. Permite a implementação de serviços interactivos, acesso à Internet e televisão. À medida que a tecnologia melhora, muitos equipamentos estão a tornar-se tão capazes quanto os computadores normais quando se trata de navegação na web e até mesmo vídeo na Internet (Video-on-Demand e streaming de vídeo). O projecto de estágio “NONIUS.TV na Smart TV LG Pro:Centric” foi desenvolvido na empresa Nonius Software que está inserida no ramo das telecomunicações. Uma das suas áreas de actividade está relacionada com o desenvolvimento de plataformas de entretenimento para o mercado hoteleiro, combinando diversos serviços e funcionalidades a pensar no hóspede. Este projecto teve como finalidade implementar alguns dos serviços e funcionalidades já existentes em plataformas que usam uma Set-Top Box da Nonius Software, numa Smart TV, aproveitando também para inovar e criar novos serviços. Nesse conjunto está incluída a implementação de uma Caixa de Mensagens, Serviço de Quartos, Serviço de Desporto e Lazer, Serviços Informativos, um cliente RTSP, um despertador, um sistema de mudança de idioma e outras pequenas funcionalidades desenvolvidas ao longo de toda a aplicação. Esta dissertação apresenta um estudo sobre as tecnologias Smart TV existentes no mercado, assim como as vantagens e desvantagens da sua utilização para este projecto. Após uma análise de requisitos de forma a estruturar e desenhar os serviços e funcionalidades a serem criados para a aplicação, implementou-se um conjunto de serviços, usando a linguagem de programação ActionScript 2.0, que permitiram à empresa disponibilizar um novo produto baseado na televisão Pro:Centric da LG.

Makespan computation for GPU threads running on a single streaming multiprocessor

Graphics processors were originally developed for rendering graphics but have recently evolved towards being an architecture for general-purpose computations. They are also expected to become important parts of embedded systems hardware -- not just for graphics. However, this necessitates the development of appropriate timing analysis techniques which would be required because techniques developed for CPU scheduling are not applicable. The reason is that we are not interested in how long it takes for any given GPU thread to complete, but rather how long it takes for all of them to complete. We therefore develop a simple method for finding an upper bound on the makespan of a group of GPU threads executing the same program and competing for the resources of a single streaming multiprocessor (whose architecture is based on NVIDIA Fermi, with some simplifying assunptions). We then build upon this method to formulate the derivation of the exact worst-case makespan (and corresponding schedule) as an optimization problem. Addressing the issue of tractability, we also present a technique for efficiently computing a safe estimate of the worstcase makespan with minimal pessimism, which may be used when finding an exact value would take too long.

People counting system using existing surveillance video camera

The Casa da Música Foundation, responsible for the management of Casa da Música do Porto building, has the need to obtain statistical data related to the number of building’s visitors. This information is a valuable tool for the elaboration of periodical reports concerning the success of this cultural institution. For this reason it was necessary to develop a system capable of returning the number of visitors for a requested period of time. This represents a complex task due to the building’s unique architectural design, characterized by very large doors and halls, and the sudden large number of people that pass through them in moments preceding and proceeding the different activities occurring in the building. To achieve the technical solution for this challenge, several image processing methods, for people detection with still cameras, were first studied. The next step was the development of a real time algorithm, using OpenCV libraries and computer vision concepts,to count individuals with the desired accuracy. This algorithm includes the scientific and technical knowledge acquired in the study of the previous methods. The themes developed in this thesis comprise the fields of background maintenance, shadow and highlight detection, and blob detection and tracking. A graphical interface was also built, to help on the development, test and tunning of the proposed system, as a complement to the work. Furthermore, tests to the system were also performed, to certify the proposed techniques against a set of limited circumstances. The results obtained revealed that the algorithm was successfully applied to count the number of people in complex environments with reliable accuracy.

Personalisation of Networked Video

Following targeted advertising and product placement, TV and online media needs more personalised methods of engaging viewers by integrating advertising and informational messages into playout content, whether real-time broadcast or on-demand. Future advertising solutions need adaptivity to individuals or on-line groups to respond to the commercial requirements of clients and agencies.

Personalised placement in networked video

Personalised video can be achieved by inserting objects into a video play-out according to the viewer's profile. Content which has been authored and produced for general broadcast can take on additional commercial service features when personalised either for individual viewers or for groups of viewers participating in entertainment, training, gaming or informational activities. Although several scenarios and use-cases can be envisaged, we are focussed on the application of personalised product placement. Targeted advertising and product placement are currently garnering intense interest in the commercial networked media industries. Personalisation of product placement is a relevant and timely service for next generation online marketing and advertising and for many other revenue generating interactive services. This paper discusses the acquisition and insertion of media objects into a TV video play-out stream where the objects are determined by the profile of the viewer. The technology is based on MPEG-4 standards using object based video and MPEG-7 for metadata. No proprietary technology or protocol is proposed. To trade the objects into the video play-out, a Software-as-a-Service brokerage platform based on intelligent agent technology is adopted. Agencies, libraries and service providers are represented in a commercial negotiation to facilitate the contractual selection and usage of objects to be inserted into the video play-out.

TV Recommendation and Personalization Systems: Integrating Broadcast and Video On-demand Services

he expansion of Digital Television and the convergence between conventional broadcasting and television over IP contributed to the gradual increase of the number of available channels and on demand video content. Moreover, the dissemination of the use of mobile devices like laptops, smartphones and tablets on everyday activities resulted in a shift of the traditional television viewing paradigm from the couch to everywhere, anytime from any device. Although this new scenario enables a great improvement in viewing experiences, it also brings new challenges given the overload of information that the viewer faces. Recommendation systems stand out as a possible solution to help a watcher on the selection of the content that best fits his/her preferences. This paper describes a web based system that helps the user navigating on broadcasted and online television content by implementing recommendations based on collaborative and content based filtering. The algorithms developed estimate the similarity between items and users and predict the rating that a user would assign to a particular item (television program, movie, etc.). To enable interoperability between different systems, programs characteristics (title, genre, actors, etc.) are stored according to the TV-Anytime standard. The set of recommendations produced are presented through a Web Application that allows the user to interact with the system based on the obtained recommendations.

Análise de Desempenho e Recomendação para Soluções IVR

Mestrado em Engenharia Informática, Área de Especialização em Tecnologias do Conhecimento e da Decisão

Behind video lectures in a MOOC

The year 2012 was the “boom year” in MOOC and all its outstanding growth until now, made us move forward in designing the first MOOC in our Institution (and the third in our country, Portugal). Most MOOC are video lectured based and the learning analytic process to these ones is just taking its first steps. Designing a video-lecture seems, at a first glance, very easy: one can just record a live lesson or lecture and turn it, directly, into a video-lecture (even here one may experience some “sound” and “camera” problems); but developing some engaging, appealing video-lecture, that motivates students to embrace knowledge and that really contributes to the teaching/learning process, it is not an easy task. Therefore questions like: “What kind of information can induce knowledge construction, in a video-lecture?”, “How can a professor interact in a video-lecture when he is not really there?”, “What are the video-lectures attributes that contribute the most to viewer’s engagement?”, “What seems to be the maximum “time-resistance” of a viewer?”, and many others, raised in our minds when designing video-lectures to a Mathematics MOOC from the scratch. We believe this technological resource can be a powerful tool to enhance students' learning process. Students that were born in digital/image era, respond and react slightly different to outside stimulus, than their teachers/professors ever did or do. In this article we will describe just how we have tried to overcome some of the difficulties and challenges we tackled when producing our own video-math-lectures and in what way, we feel, videos can contribute to the teaching and learning process at higher education level.

Video-­‐monitorization system for a realistic driving simulator

Nos últimos anos, o ISEP em colaboração com a FEUP e outras Universidades, criou um simulador realista de condução chamado DRIS, que tem como objectivo ajudar em trabalhos de investigação de diferentes áreas, como engenharia civil, computação gráfica, psicologia, educação, etc. O resultado deste trabalho pretende ajudar os profissionais a analisarem os dados recolhidos em cada experiência de condução, a fim de permitir o estudo das reações do motorista em diferentes obstáculos durante um percurso. O simulador DRIS é constituído por uma tela branca, onde os ambientes de simulação são projetados; um carro real, onde é feita a experiência de condução e quatro câmaras colocadas no carro. Destas quatro câmaras, três estão dentro do carro e uma fora do carro. Cada câmara está focada estrategicamente, em partes críticas da condução: a estrada, o motorista, os pedais e os controles (mudança de marcha, volante, os comandos do limpador, etc). Cada uma das câmaras grava um vídeo, que é guardado em um computador colocado em uma das salas de controlo, dentro do Laboratório de Análise de Tráfego na FEUP. Além disso, um arquivo de texto é guardado no mesmo computador. Este arquivo de texto contém algumas informações sobre a experiência do motorista, como as coordenadas do carro, a velocidade do carro, o tempo, etc O trabalho desta Tese surge com a finalidade de melhorar a forma de os profissionais analisar e interpretar os dados recolhidos a partir de uma experiência de condução no DRIS. Para o efeito, foi criado um sistema de vídeo-­‐monitorização, que consiste em uma aplicação de vídeo, que permite a visualização de quatro vídeos simultaneamente, e ler um arquivo de texto, que contém todos os dados recolhidos na experiência. Ambos (vídeo e texto) têm de estar sincronizados com o mesmo tempo de forma a permitir ao utilizador, navegar backward e forward com a ajuda de um cursor. Além disso, como qualquer reprodutor de vídeo básico, contém alguns botões para controlar o status do vídeo (Play, Stop, Pause) e permiti que os profissionais analisem com detalhe os dados dos quatro vídeos. Aproveitando os avanços no desenvolvimento de software, a aplicação foi feita em C++ usando a biblioteca Qt, em ambiente de desenvolvimento integrado do Qt Creator, o que tornou mais fácil a implementação. No fim deste relatório (capítulo 4) é anexado um manual do usuário, a fim de explicar e ajudar os profissionais a usar a aplicação.

Social Media Integration in Video Games: A Social Overlay for Desktop Games

Simpósio de Informática (INForum 2015), Covilhã, Portugal. Notes: Best paper award nominee.

Designing video lectures for MOOC

Educational videos differ from other teaching and learning technologies as they allow the benefit of using visual perception. Video lectures are not new to education, however with the use of innovative video technologies they can improve academic outcomes and extend the reach of education. They may offer extraordinary new experiences for higher education institutions (HEI). Through them lecturers can provide information and contents to students, and if used creatively, video lectures can become a powerful technological tool in education, inside and outside classrooms. Inside a classroom it can motivate students and improve topics’ debate and outside it is a good support for students’ self- learning. In some cases they can be used to work some subjects standing behind, but needed to support actual courses contents, that students do not remember (or were not even taught), opening an “in front to the past door” that backs students self-study. The student-educator dynamic is changing. Students are expecting exceptional instruction and educators are expecting students to be more and more well informed about subjects from online viewing.This article explores some of the potential benefits and challenges associated with the use of video lectures in the teaching and learning process at higher education. We will also discuss some thoughts and examples for the use of teaching materials to enhance student’s learning and try to understand how video can act as powerful and innovative to enlighten teaching and learning (note that unfortunately, sometimes, the opposite is happening).

Proposta de solução de videovigilância para locais remotos

Desde tempos remotos que homens faziam a vigilância de bens e mercadorias e mais recentemente também de pessoas com o intuito de dissuadir roubos, atos de vandalismo e de violência. Nos últimos anos, com a evolução das novas tecnologias verificou-se a sua adoção para auxílio da vigilância. Os atos de terrorismo que têm acontecido um pouco por todo o mundo trouxeram um clima de insegurança à população mundial. Este fenómeno, juntamente com o elevado número de roubos e atos de violência levou à expansão de utilização dos meios de videovigilância de forma a dissuadir estes tipos de crime podendo mesmo, nalguns casos servir como prova para punir os autores dos mesmos. Em Portugal tem-se verificado uma escalada de crimes nas zonas mais rurais não só de bens como as alfaias agrícolas mas também de frutos e mesmo de animais. Estes crimes predominam em locais rurais, relativamente distantes das povoações e em locais onde não existem (ou são praticamente inexistentes) infraestruturas necessárias para implementar meios de videovigilância como a falta de rede elétrica e internet o que torna quase inviável a existência de sistemas de videovigilância nesses locais. Dotar esses locais das infra estruturas necessárias poderia tornar-se demasiado dispendioso e os vigilantes humanos poderiam correr riscos no meio dos montes ou noutros locais remotos para além dos seus elevados custos. Para além do problema dos roubos, existe um outro flagelo relacionado com os incêndios na floresta portuguesa, que todos os anos é dizimada pelo fogo devido a incêndios que surgem na sua maioria causados pelo homem sendo uma parte significativa os de origem criminosa. Para dar resposta a estes problemas e no sentido de vigiar e dissuadir estes tipos de crimes, iniciamos um estudo que pretende propor um protótipo de um sistema de videovigilância para locais remotos (SVR - Sistema de Videovigilância Remota) de baixo custo de forma a diminuir o número de crimes e assim minimizar os prejuízos económico e sociais causados pelos mesmos. Pretendemos estudar o problema e analisar tecnologias com potencial para propor uma solução que possa auxiliar a vigilância nesse tipo de locais com o pressuposto de poder vir a contribuir para a diminuição deste tipo de crimes devido ao seu efeito dissuasor pelo facto de se poder divulgar que estes locais já têm uma solução de vigilância oculta. A solução proposta contempla um sistema de videovigilância com uma camara construída com base num Raspberry Pi onde o vídeo é transmitido em streaming via Web através de comunicações móveis. A alimentação do sistema nestes espaços sem energia elétrica é feita através de um painel fotovoltaico. É proporcionado ao utilizador uma interface para visualizar o vídeo transmitido e um mecanismo de notificações por email. É ainda possível a visualização de imagens gravadas num cartão de memória relativas a ocorrências de deteção de movimentos. Foram realizados inúmeros testes ao protótipo SVR sendo os resultados obtidos aqui descritos.

Social Media Integration in Video Games GameNshare: A Social Overlay for Desktop Games

The ever increasing popularity of social media makes it a promising source for the personalization of gameplay experiences. Furthermore, involving social network friends in a game can greatly enrich the satisfaction of the player and also attract potential novel players to a game. This master thesis describes a social overlay designed for desktop games, called GameNshare. It allows players to easily capture and share with multiple social networks game-related screenshots, videos and stories. Additionally, it also provides asynchronous multiplayer game mechanics to directly integrate social network friends in the game. GameNshare was designed to interact with the users in a non-intrusive way allowing them to be in complete control of what is shared. It prevents unsolicited sharing of messages, a key problem in social media integration tools, by the use of built-in message monitoring and anti-spam measures. GameNshare was specially designed for players aged from 18 to 25 years that are regular users of Twitter and Facebook. It was tested by a group of 10 individuals from the target age range that were surveyed to capture their insights on the use of the social overlay. The implemented GameNshare features were well accepted by the testers that were also useful in highlighting features for future development. GameNshare ultimate goal is to make players look and ask for social integration and allow them to take full advantage of their social communities to improve gaming experiences.