Carregando...
 

Image
 

Trabalhos Aceitos


Uma câmera inteligente para reconhecimento automático de frame markers

This report describes the experience of a team of three computer science and engineering undergrad students to conceive a potentially innovative product targeting a children audience. The solution is a game where the children have to choose a puzzle from a library and assemble it manipulating physical blocks. The VOXAR Puzzle, as it was named, uses vision technology to track the blocks. This has allowed the team to build a tangible interface that is totally controlled by the physical blocks. Furthermore, the process used for the development of the game platform had innovation in mind. The students had to interact with designers both in person and remotely. Beyond, from the early stages of the project they had to interact with schools teachers and children to validate the prototype. A simple Blue Ocean strategy was used to define the functionalities and features of the game platform, comparing it with relevant competitors. The final result was a prototype with a professional interface that was validated with users, children from a public school in Recife.
 
Membros:
- Cristiano Araújo (Universidade Federal de Pernambuco - Brazil)
- André Silva (Centro de Informática - Brazil)
- Caio Lins (Federal University of Pernambuco - Brazil)
- Vinicius Silva (Centro de Informática - Brazil)

Projeto QualisFruit

The agricultural hub of Petrolina and Juazeiro is considered the most dynamic pole of the backlands of Pernambuco and Bahia, and are distinguished by high export of mango, especially the kind of "Tommy Atkins".

However, one of the great difficulties of producers is to determine the point of harvest, since fruits do not ripen prematurely harvested or are irregularly shaped and this is reflected in the amount of sugars and acidity of mango. On the other hand, a late harvest reduces the lifetime and makes the fruit more sensitive to mechanical damage and attack by micro- organisms.

Thus, to meet the demand for export of fruits, one should ensure the quality of the fruits that are harvested in this region. One tool that can assist in this task is the digital image processing, where the fruits may have set the point of harvest, based on analysis of their appearance to meet the market it is intended for.

In this work a system for detecting the point of harvest mango "Tommy Atkins" through methods of converting the RGB (Red, Green, Blue) and HSV (hue, saturation, value) is presented, using only integers and being able to detect the stage of ripeness second criterion developed by Embrapa.
The current project will eventually operate in remote monitoring of orchards, with the aid of Unmanned Aerial Vehicles (UAV), called drones, and, given his analysis performed in hardware, and software featuring more processing capacity to integrate new features the system. 

Membros:
- Camila Nunes (Universidade Federal de Pernambuco - Brazil)
- Vanessa Carvalho (Universidade Federal de Pernambuco - Brazil)
- Vanessa Ogg (Universidade Federal de Pernambuco - Brazil)
- Edna Barros (UFPE - Brazil)

System of people detection and counting embedded in a model aircraft (Sistema de detecção e contagem de pessoas embarcado em um aeromodelo)
 
Computer vision is a branch of computer science that has a wide range of applications. Adding these features to an aerial vehicle provides several possibilities, particularly in the area of security and, especially, to rescue people. A drone or an airplane flying over a region can, besides giving an overview of the site, identifying attackers in a perimeter, can also assist in surveillance activities and help to find people. The system will be an unmanned aerial vehicle that uses the computational power of the platform to support computer vision, recognizing and counting people in a particular place. The vehicle can fly and be controlled by manual control. Image sequences will be captured and, for each 25 images, algorithms for people recognition and identification will be applied with the aid of opencv. For the image processing, the Intel Atom processor will be used. As tools, we will adopt the C++ language embedded in GNU / Linux operating system. Through a supervisory system, you can select a region of interest on a map and define the area to be monitored. The software will also show information received from vehicle’s sensors and processed images of camera through use of networks and TCP / IP protocols. The processing will be performed on the main board DE2i-150 (Cyclone IV) and sent through Wi-Fi to a computer that will be used with the monitoring system. The techniques Feature Extraction Pixel and Histograms of Oriented Gradients were those that yielded best accuracy indices for human detection.
 
Membros:
- Ricardo Jacomini (Escola Politécnica, Universidade de São Paulo / Faculdade de Tecnologia Termomecanica - Brazil)
- Rafael Lillo (Faculdade de Tecnologia Termomecanica - Brazil)
- Vitor Fiorillo (Faculdade de Tecnologia Termomecanica - Brazil)
- Vitor Longarini (Faculdade de Tecnologia Termomecanica - Brazil)

Plataforma embarcada para captura e estabilização de imagens aéreas adquiridas por VANTs
 
The objective of this project is to perform image capture from a camera connected directly to the pins available on the board and perform a pre-processing video stabilization. After application of noise vibration filter using Kalman Filter, the stream is available for viewing or for more elaborate processing to detect information in the stabilized image. The development of this project consists of two blocks: capture and image processing performed on FPGA (Field Programmable Gate Array) and post-processing and visualization executed by the software running on the processor.
 
Membros:
- Maikon Bueno (Universidade Federal de Mato Grosso - Rondonópolis - Brazil)
- Izabela Pereira (Universidade Federal de Mato Grosso - Rondonópolis - Brazil)
- Mateus Monteiro (Universidade Federal de Mato Grosso - Rondonópolis - Brazil)
- Otavio Nantes (Universidade Federal de Mato Grosso - Rondonópolis - Brazil)

Safe Swimming Pool: um Sistema de Monitoramento para a prevenção de afogamentos em Piscinas
 
O Sistema Embarcado a ser desenvolvido foi denominado: “Safe Swimming Pool: um Sistema de Moni- toramento para a prevenção de afogamentos em Piscinas”. Este sistema baseia-se em vídeo vigilância inteligente (recorrendo a imagens de vídeo capturadas de câmeras comuns) com a capacidade de detec- tar de forma autônoma as atividades de utilizadores de uma piscina doméstica e disparando um alerta caso detecte um comportamento de afogamento.
 
Membros:
- Leandro Martinez (Universidade de Sao Paulo - Brazil)
- Carlos Roberto P Almeida Jr (Universidade de Sao Paulo - Brazil)
- Eduardo Marques (Institute of Mathematics and Computation - RCL (Reconfigurable Computing Labs) - Brazil)
- José Arnaldo Mascagni de Holanda (University of São Paulo - Brazil)

Patrulha Virtual
 
Nós propomos um sistema de vigilância remota em que o vigilante controla um pequeno veículo através de uma conexão WiFi. O sistema foi idealizado para auxiliar a patrulha dentro de um campus universitário, o qual possui conectividade sem fio. O veículo possui uma câmera digital integrada e faz o streaming das imagens captadas para o vigilante que as visualiza através de um sistema visual do tipo Head­mounted display. Tal sistema permite o controle da orientação angular da câmera através de movimentos da cabeça do vigilante, ou seja, a câmera instalada no veículo imita os movimentos da cabeça do operador.
 
Membros:
- Sérgio Aurélio Ferreira Soares (Universidade Federal do Vale do São Francisco - Brazil)
- João Gabriel Reis (UFSC - Brazil)
- Antonio Carlos Luppi Junior (UFSC - Brazil)
- Antônio Augusto Fröhlich (Universidade Federal de Santa Catarina - Brazil)

Tracking de carro robô através de câmera em drone e processamento via FPGA
 
Nesse sistema, uma sequência de imagens será recebida via WIFI. Usando o barramento PCIe, uma imagem de cada duas da sequência será passada para o FPGA. A sequência de imagens será transmitida a uma frequência de 24 fps (frames per second) e o uso de apenas 12 frames é uma estratégia de aceleração do processamento, sem perca de qualidade. A sequência de ima- gens será capturada de um ambiente real por um drone com uma câmera. Nesse ambiente real, existe um carro robô com um marcador colorido preso ao teto e visível à câmera que está capturando as imagens. 
 
Membros:
- Roger Resmini (Universidade Federal de Mato Grosso - UFMT/Rondonópolis - Brazil)
- Maurício Lemos (UFMT - Brazil)
- Flavio Brietenbach (UFMT - Brazil)
- Gustavo Silva (UFMT - Brazil)

Projeto GuideME
 
GuideMe is an assistive application for visually impaired people which combines wearable computer technology with advanced sensor fusion algorithms to improve user accessibility. The introduced prototype, based on a D2i-150 Terasic hardware platform, runs GNU/Linux operating system and a collection of 100% open source tools. The application architecture and specific software parts were designed and implemented for the project. With the aid of a low-cost CCD camera and a set of image processing and patter recognition algorithms, GuideMe is able not only to detect the proximity of objects, but can perceive the presence of other people, and even identify their faces from a database. Through a voice synthesizer functionality, GideMe can inform the user if someone approaches him or how many people are around. This functionality, by itself, is a step forward with respect to electronic white canes which only detect obstacles. The most innovative capability of GuideMe, however, is the way it combines the information from two sonar sensores to produce a stereophonic 3D sound. Using triangulation, it computes the relative position of obstacles and, by means of an interferometer-based technique, creates a stereophonic 3D sound which appears to come from the corresponding direction, thus conveying the user a spatial sensations through which he can orient in the physical environment.
 
Membros:
- Francisco Monaco (ICMC - Universidade de Sao Paulo - Brazil)
- Rene Pinto (University of Sao Paulo - Brazil)
- Luiz Henrique Nunes (ICMC-USP - Brazil)
- Heitor Freitas (USP - Brazil)

Gerenciamento de chaves criptográficas para redes de dispositivos móveis
 
The increase usage of wireless networks in general and sensing devices, and the Internet of Things (IoT) deployment, raise concerns on data privacy and authenticity. How could cryptographic primitives be used to achieve such services on resource constrained devices?
In this work, we implemented an efficient cryptographic key management approach for mobile wireless networks, such as wireless sensor networks and IoT. Our approach provides services including cryptographic key distribution and revocation, and network node admission.
To achieve certification of the sensors' cryptographic keys we have used the Elliptic Curve Qu-Vanstone implicit certificate scheme (ECQV), which is intended as a general purpose certificate scheme for applications within computer and communications systems. It is particularly well suited for application environments where resources such as bandwidth, computing power and storage are limited. ECQV provides a more efficient alternative to traditional certificates. The protocol only involves one scalar multiplication operation for key generation, which is the most expensive operation in our scenario.
The server application was deployed on the DE2i-150 board. It has two modes of operation: software only (using Relic running on the Atom processor) and hardware accelerated (most expensive operations are implemented on the FPGA). The hardware accelerated implementation is about 4 times slower than its software only counterpart, mostly because of the time taken to transfer data to internal FPGA registers, but we believe that further improvements could lead to a better hardware.
 
Membros:
- Geovandro Pereira (Escola Politécnica, University of Sao Paulo - Brazil)
- Bruno Oliveira (Escola Politécnica da Universidade de São Paulo (EPUSP) - Brazil)
- Luckas Farias (Escola Politécnica da Universidade de São Paulo (EPUSP) - Brazil)
- Bruno Albertini (Escola Politécnica da Universidade de São Paulo (EPUSP) - Brazil)
- Cintia Margi (Universidade de São Paulo - Brazil)

Sistema de Prognósticos de Doenças Correlatas a Dengue
 
O sistema terá como função, fazer a coleta dos dados sintomáticos do paciente e, à partir destes, correlacionar com um banco de dados de doenças e sintomas, que utilizando lógica fuzzy, será capaz de inferir estatisticamente qual a possível doença o paciente terá contraído. Com este tipo de análise de correlação entre doenças e sintomas, é possível analisar de forma precisa e clara as possíveis doenças de acordo com n fatores relacionados a cada uma e estimar probabilisticamente qual doença tem mais chance de ocorrer de acordo com os dados inseridos a inicialmente.
 
Membros:
- Rychelly Ramos (Federal Institute of Education, Science and Technology of Paraíba - Campus Campina Grande - Brazil)
- Gustavo Silva (Federal Institute of Education, Science and Technology of Paraíba- Campus Campina Grande - Brazil)
- Paulo Ribeiro Lins Júnior (Instituto Federal de Educação, Ciência e Tecnologia da Paraíba - Brazil)
- Jarbas Silva (Federal Institute of Education, Science and Technology of Paraíba - Campus Campina Grande - Brazil)

Simulador de realidade virtual para automação e treinamento
 
Desenvolver um simulador em tempo real capaz de reproduzir o comportamento de uma planta industrial, tais como montador de cargas, guindaste de posicionamento, esteira de transporte classificador, planta industrial para produção de tintas. O simulador devolverá ao usuário imagens tridimensionais, som e respostas idênticas ou semelhantes a uma estrutura real.
 
Membros:
- Gabriel Lopes (University of São Paulo - Brazil)
- Rafael Ring (Universidade de Sao Paulo - Brazil)
- Ricardo Boccoli Gallego (Escola Politécnica da Universidade de São Paulo - Brazil)
- Eduardo Pellini (EPUSP/PEA - Brazil)

Um sistema embarcado de tempo-real para experimentos de neurociência retroalimentados
 
A complete data acquisition and signal output control system for synchronous stimuli generation, geared towards in vivo neuroscience experiments, was developed using the Terasic® DE2i-150 board. All emotions and thoughts are an emergent property of the chemical and electrical activity of neurons. Most of these cells are regarded as excitable cells (spiking neurons), which produce temporally localized electric patterns (spikes). Researchers usually consider that only the instant of occurrence (timestamp) of these spikes encodes information. Registering neural activity evoked by stimuli demands timing determinism and data storage capabilities that cannot be met without dedicated hardware and a hard real-time operational system (RTOS). Indeed, research in neuroscience usually requires dedicated electronic instrumentation for studies in neural coding, brain machine interfaces and closed loop in vivo or in vitro experiments. We developed a complete embedded system solution consisting of a hardware/software co-design with the Intel® Atom processor running a free RTOS and a FPGA communicating via a PCIe-to-Avalon bridge. Our system is capable of registering input event timestamps with 1μs precision and digitally generating stimuli output in hard real-time. The whole system is controlled by a Linux-based Graphical User Interface (GUI). Collected results are simultaneously saved in a local file and broadcasted wirelessly to mobile device web-browsers in an user-friendly graphic format, enhanced by HTML5 technology. The developed system is low-cost and highly configurable, enabling various neuroscience experimental setups, while the commercial off-the-shelf systems have low availability and are less flexible to adapt to specific experimental configurations.
 
Membros:
- Lirio Almeida (Universidade de Sao Paulo - Instituto de Fisica de Sao Carlos - Brazil)
- Paulo Matias (University of São Paulo - Brazil)
- Rafael Guariento (Universidade de Sao Paulo - Instituto de Fisica de Sao Carlos - Brazil)

Análise de disformidades em plantações agrícola com drone
 
The system developed is proposed to optimize the scans process of agricultural areas for precision agriculture. Scans agricultural areas aims to map the rural environment for patterns indicating deformities in planting. This helps farmers to identify, prevent and correct possible problems in crops - such as the presence of pests, burned areas, or any
other abnormality in cultivation.
In the developed system, we simulated the use of drone to achieve the mappings. The main problem in the use of these aircraft is the autonomy of their batteries. The consumption of a battery charge cycle takes approximately 20 minutes (at most). In order to improve the performance of the process as a whole, our system offers an optimization of the route to be traveled by quadcopters in order to save energy of the device because of the limitation in the use of the battery.
Basically, the proposed mapping of the region and scanning process would consist of two stages. At first, the drone overflys the area to be mapped in order to recognize the misshapen planting, but this step is not performed with simulated air-flights of quadcopter but with images obtained from Google Earth, which prove sufficient geographical information for the calibration of application in this first phase. Then, with the images obtained from Google Earth, the OpenCV library, which is an abstraction level computer vision to facilitate digital image processing required for capturing the possible sources of deformity of planting and consequently the points used will be used in calculating the route algorithm of the second stage.
 
Membros:
- Francielly Grigorio (Universidade Federal da Paraiba - Brazil)
- Gustavo Henrique Silva Sobral (Federal University of Paraiba - Brazil)
- Euler Bakke Duarte de Souza (Federal University of Paraiba - Brazil)
- Alisson Brito (Universidade Federal da Paraiba - Brazil)

Controle e Monitoramento de Robôs Móveis através de Simulação Hardware-in-the-loop
 
A ideia principal desta proposta é desenvolver um robô móvel que seja capaz de compar- tilhar todas as suas informações em tempo real com vários tipos de simuladores de forma distribuída.
 
Membros:
- Alisson Brito (Universidade Federal da Paraiba - Brazil)
- Luís Feliphe Silva Costa (Universidade Federal da Paraíba - Brazil)
- José Cláudio Vieira Junior (Universidade Federal da Paraíba - Brazil)
- Ricardo Costa (UFPB - Brazil)

Utilização de um sistema embarcado para tomada de deci- são em plantações de Cana-de-açúcar baseado na Agricultura de Precisão
 
The present scenario of sugar-cane industry at the Brazilian Northeast region is highly degraded due to misapplication of funds and production structuring. This paper:Using an embedded system for making decisions in sugar cane plantations based on Precision Agriculture, proposes the use of intel DE2i-150 board to manage collected data from distributed sensors in a field of sugar cane sugar cane. Due to lack of resources, the short time to develop the project, and little knowledge of the technologies to be used, we seek an alternative to test the processing power of the board on an geoprocessing application. We found the option to simulate sending data from sensors through inserts into a geographic database (present in the Geographic Information System we used) made by local network, but there was no time to complete this simulation. What we done to demonstrate the potential of the board within the scope of our idea was to plot maps of cities and states with data provided by local government. Therefore, we used a GIS installed on Windows 7. With the GIS installed, we were able to test the potential of the board in terms of data processing and generation of maps with these data (graphics processing). Leaving the data insertion simulation via local network, communication with sensors and using the FPGA for data processing, for future work.
 
Membros:
- Alisson Brito (Universidade Federal da Paraiba - Brazil)
- Alisson Lacerda (UFPB - Brazil)
- Janislley Oliveira (Universidade Federal da Paraíba - Brazil)
- Paulo Henrique Silva (Universidade Federal da Paraíba - Brazil)

eHEMOGRAMA: Sistema de contagem e caracterização morfológica de células sanguíneas
 
Essa proposta trata do projeto e implementação de um sistema embarcado de baixo custo destinado à contagem de hemácias, plaquetas e leucócitos, bem como sua caracterização morfológica.
 
Membros:
- Antonio Marcus Nogueira Lima (Universidade Federal de Campina Grande - Brazil)
- Caio Barbosa (UNIVERSIDADE FEDERAL DE CAMPINA GRANDE - Brazil)
- Leonardo de Almeida e Bueno (Federal University of Campina Grande - Brazil)
- Eduardo Pereira (Universidade Federal de Campina Grande - Brazil)

Access control and ticketing for public transport
 
Desenvolvimento de um sistema de controle de acesso embarcado. O sistema embarcado é constituído pela plataforma que a Intel fornecerá, webcam, leitor rfid, visor, pen-drive, cartão de memória, leds, mini-speakers e contará também com uma bateria independente do veículo. Este sistema exibirá no visor a quantidade de créditos restantes no cartão do usuário e o número de passageiros com o status liberado. Haverá também leds (verde para liberado e vermelho para negado) e sons (bips curtos para liberado e bips longos para negado) que indicarão o status de acesso.
 
Membros:
- Pedro Mourão (Universidade Federal de São João Del Rei - Brazil)
- Thais Rios (Universidade Federal de São João Del Rei - Brazil)
- Sergio Oliveira (Universidade Federal de São João del Rei - Brazil)

Sistema Computacional para realização de Exame de Visão Periférica
 
The impact of visual loss has deep implications on a person's life, affecting not only their personal appearance, but also your financial and its social side. Some causes of blindness are not reversible through surgical treatment such as Glaucoma. One way of detecting the Glaucoma level is through the Peripheral Vision Exam, also known as Automated Perimetry. The results of this exam can be associated with other methods and analysis techniques to improve the accuracy of the diagnosis, helping the doctor make fast and precise conclusions about the patient disease. This paper proposes a prototype of equipment capable to do the peripheral vision exam, submitting the patient to graphical tests monitored by a camera that tracks his eyes in real time. To implement this functionality the DE2-150i platform was used. The ATOM processor was used to implement the graphical interface of the exam and the FPGA is responsible to the image processing for the eye-tracking. The results of this exam can be used to assist the doctor to promptly diagnose diseases correlated with eye issues. The prototype may be useful in treating medical conditions that are related to peripheral vision issues.
 
Membros:
- João Pedro Carvalho de Souza (Federal University of Juiz de Fora - Brazil)
- Vinicius Murilo Lima Rodrigues (Federal University of Juiz de Fora - Brazil)
- Vinicius Lagrota Rodrigues da Costa (Federal University of Juiz de Fora - Brazil)
- Leandro Rodrigues Manso Silva (Federal University of Juiz de Fora - Brazil)

Smart traffic monitor based on image capture sensors installed on the infrastructure
 
O projeto consiste em um sistema de monitoramento em tempo real do fluxo de veículos, utilizando como fonte de informação imagens capturadas por câmeras instaladas em pontos estratégicos da infraestrutura rodoviária. O cenário completo consiste de um servidor e diversos nodos distribuídos geograficamente. O servidor será um computador convencional, e deverá armazenar um banco de dados com as informações enviadas por todos os nodos. Cada nodo seria composto por uma unidade CPU+FPGA para processamento de imagens, obtenção e transmissão de informações para o servidor.
 
Membros:
- Lucas Hartmann (Federal University of Parahyba - UFPB - Brazil)
- Jonyelison Alves (Federal University of Parahyba - UFPB - Brazil)
- Filipe Freitas (Federal University of Parahyba - UFPB - Brazil)
- Diogo Yokoyama (Federal University of Parahyba - UFPB - Brazil)

Interface para Verificação Funcional Automática em FPGA com UVM
 
O sistema a ser desenvolvido é uma interface para verificação funcional automática em FPGA. A partir da arquitetura da placa DE2i a ser utilizada e baseado na metodologia Universal Verification Methodology (UVM), a ideia proposta consiste em criar uma etapa no processo de verificação, na qual o Design Under Test (DUT), simulando na FPGA, pode se comunicar com o testbench, executando na CPU, dessa forma será possível realizar a verificação em tempo real.
 
Membros:
- Adalberto Teixeira Jr (Universidade Federal de Campina Grande - Brazil)
- Samir Feitosa (Universidade Federal de Campina Grande - Brazil)
- Matheus Batista (Universidade Federal de Campina Grande - Brazil)
- Elmar Uwe K. Melcher (Universidade Federal de Campina Grande - UFCG - Brazil)

SIME - Sistema Integrado de Medição de Energia
 
O Sistema Integrado de Medição de Energia (SIME) é uma ferramenta de telemetria para medição continua de consumo de energia. O sistema proposto é composto por duas instâncias de componentes microprocessados, sendo uma Unidade de Controle e Gerenciamento (UCG) e uma Unidade de Medição e Análise (UMA), representados respectivamente pelos kits Altera DE2i-150 e Arduino Uno. O SIME apresenta uma arquitetura onde se enquadra nas aplicações AMR (Automatic Meter Reading) e AMI (Advanced MeteringInfrastructure), que são um dos conceitos do Smart Grid. Onde a aplicação AMR elimina a necessidade da visita do leiturista ao consumidor. 
 
Membros:
- Gláuber Azevedo (UNIFACS - Brazil)
- Pedro Duff (UNIFACS - Brazil)
- Euclerio Ornellas (UNIFACS - Brazil)
- Fábio Santana (UNIFACS - Brazil)

Vê-HDR
 
A ideia do projeto Vê-HDR é desenvolver um sistema capaz de realizar filmagem HDR. O sistema proposto consiste em obter continuamente três imagens simultâneas, a partir de três câmeras com diferentes valores de exposição e produzir em tempo real a imagem HDR resultante.
 
Membros:
- Isaac Pessoa (UFPB - Brazil)
- Zariff Meira (UFPB - Brazil)
- João Dantas (UFPB - Brazil)
- Hugo Lima (UFPB - Brazil)

Sistema de Detecção de Obstáculos em Tempo Real
 
The use of bicycles is being encouraged all around the world, as a less traffic­ generating and more eco­ friendly vehicle. At UNICAMP, biking is a major mode of transport: unfortunately our streets (like many in Brazil and other countries) are not very safe for cyclists. They are poor lightened badly paved, with numerous holes, which causes a struggle to get across at night. All those factors makes likely for obstacles to go unnoticed, which can cause serious accidents.
In order to prevent such events, we developed BIKEBEEPS. It consists of a luminous grid projected onto the ground, associated with an active warning by sound. Obstacles can be detected by deformations in the luminous grid, using a webcam, and then applying image processing (Hough Transform) on the video stream. If the grid gets deformed by an obstacle, the sound of a beep is emitted to alert the user.
The reaction time of a normal person is approximately 0.7 seconds 1 and the average speed of bicycle in urban environment is 10km/h or 2.77 m/s. A good distance for the projection is therefore 2m, which is feasible.
For the image processing in the prototype, we have employed OpenCV, which provides extended documentation and functions aimed at realtime computer vision, such as Hough Transform and video capture, which were used to develop this project.
The project has shown good results in obstacle detection. Furthermore, all the image processing happens in real time and consumes little memory and processing, making this system computationally cheap. Also, the system can be easily extended to other transportation modes, such as cars and wheelchairs.
 
Membros:
- Ana Julia Pereira Caetano (Universidade Estadual de Campinas - Brazil)
- Raissa Machado (Universidade Estadual de Campinas - Brazil)
- Eduardo Valle (UNICAMP - Brazil)

VoiceChess: xadrez por comando de voz
 
O xadrez é um clássico jogo de estratégia, considerado também como um esporte, foi criado a mais de 1500 anos. Séculos desde sua invenção, o xadrez se espalhou para todos os países do mundo.
Entretanto, há uma diferença marcante entre esse e outros jogos populares. Enquanto o aprendizado de quase todos os jogos podem ajudar a construir a au- toestima e confiança, o xadrez é um dos poucos que exercita plenamente nossas capacidades de raciocínio. O xadrez desenvolve a memória e o raciocínio lógico, melhora a concentração e ainda promove a imaginação e criatividade.
Dito isto, a presente proposta de projeto baseia-se no desenvolvimento de um jogo de xadrez controlado por comandos de voz.
 
Membros:
- Giovani Gracioli (Universidade Federal de Santa Catarina - Brazil)
- Eloi Giacobbo (Universidade Federal de Santa Catarina - Brazil)
- Fabio Meurer (Universidade Federal de Santa Catarina - Brazil)
- William Pauli (Universidade Federal de Santa Catarina - Brazil)

Projeto USWoMI
 
O projeto USWoMI – Unified System for Workers on Menace and Injury - consiste em um sistema de monitoramento e suporte aos profissionais expostos ao risco, como bombeiros, policiais e outras atividades onde ambiente apresenta um alto grau de periculosidade, justificando um monitoramento constante deste profissional. O objetivo é desenvolver um sistema de baixo custo que é colocado na vestimenta do profissional e monitorará informações biológicas (batimentos cardíacos), a sua localização (GPS) e se comunica com um servidor central através da tecnologia GPRS, permitindo um acesso remoto às informações independentemente do local.
 
Membros:
- Eduardo Gotardi (Uniritter - Brazil)
- Leandro Rodrigues (Uniritter - Brazil)
- Cezar Rodolfo Reinbrecht (Universidade Federal do Rio Grande do Sul - Brazil)

Projeto Fisio
 
The costs to have physiotherapy equipment are expensive, it costs around six thousands reais (R$6,000.00), and therefore clinics usually have fewer electronic equipments. However for paraplegic, elderly, people with physical disability in legs to use this equipments can recover the muscle on the legs and helps the patient self- esteem, one believes that this help to recover faster. The project aims to help these patient by making a physiotherapy equipment that is twice less expensive than the regular equipments, moreover the patient may stay sitting, instead of lying down. The project uses less than 5% of the FPGA, which enables to add much more features to the project, and one uses the LCD to show the exercise configuration.
 
Membros:
- Bruna Gonzaga (Uniritter - Brazil)
- Manuela Ternes (Uniritter - Brazil)
- Lucimar Neves (Uniritter - Brazil)
- Carol Concatto (UFRGS - Brazil)

Mapeamento 3D usando LiDAR

Membros:
- Sergio Chevtchenko (UFPE - Brazil),
- Rafaella Vale (Universidade Federal Rural de Pernambuco - Brazil)
- André Moraes (Universidade Federal Rural de Pernambuco - Brazil)

Cancelamento Ativo de Ruídos em Ambientes

A equipe pretende desenvolver um sistema de escaneamento 3D baseado em tecnologia LiDAR (Light Detection and Ranging).

Membros:
- Cristina Bazzano (State University of Campinas - Brazil)
- Jheyne Ortiz (Universidade Estadual de Campinas - Brazil)
- Juliana Freitag Borin (Universidade Estadual de Campinas - Brazil)
- Mirella Esther da Silva (State University of Campinas - Brazil)

Uma abordagem hardware/software para reconhecimento do alfabeto em libras através das mãos.

About 170 thousand people in Brazil have self declared “deaf”. Because they are not able to communicate so clearly as those who does not have the disability, this portion of the population needs a written or visual mean. To cope with this need in Brazil, an official sign language pattern, called LIBRAS, that allows the communication among deaf, was developed. However, still there is a communication gap using this sign language, once only a small part of the population knows LIBRAS. Trying to reduce this gap, this approach proposes a computational solution to translate LIBRAS symbols to text symbols, through computer vision. To guarantee the real-time translation, some hardware components were built to fulfill the most expensive image processing tasks using in this project: RGB color space to YCrCb color space conversion and pixel thresholding. Once real-time videos capture produces a high number of data and the target platform have some limitation in the communication throughput, some adaptation, both in hardware and software, were required. These adaptations involve the compression of the thresholded data, a memory buffer manager and a frame collector with a data decompression software component. A series of system architectures coping with this adaptations were designed and implemented to reach desired throughput. This approach represents a initial stage of a bigger project. Although experimental results has shown that the system recognize real-time 12 LIBRAS symbols with the accuracy of 92.5%, some isolated symbol, which are represented through a sequential movement are not actually able to be detect.

Membros:
- Lucas Cambuim (Federal University of Pernambuco - Brazil)
- Rafael Macieira (Universidade Federal de Pernambuco - Brazil)
- Fernando de Paula Neto (Universidade Federal de Pernambuco - Brazil)
- Edna Barros (UFPE - Brazil)

Desenvolvimento de Dispositivo Eletrônico Móvel para Auxiliar o Diagnóstico de Glaucoma de Ângulo Aberto

Glaucoma is the second leading cause of blindness in the world. In 2010, the number of people which had the disease was around 60 million, and by 2020 this number is estimated to increase to 80 million. Besides, if not diagnosed in an early stage, glaucoma can lead to irreversible blindness. About 8.4 million people in the world is blind due to glaucoma and by 2020 this number is estimated to reach 11.2 million. In retinal images there are two regions of interest for the diagnosis of Glaucoma, they are the Optic Disc and the Optic Cup. A common way to detect glaucoma consists of analyzing the proportion between the diameters of the Disc and the Cup (Cup to Disc ratio). A ratio greater than 0.5 is a good indicative of glaucoma. In this project, a prototype of an embedded device that automatically calculates the Cup to Disc ratio from retinal images was developed. A combination of FPGA and the Atom processor was used to reduce the computational costs related to the image processing, and to create an interface and a database where is possible to keep track of the progression of the disease through the years. This portable device, which can be easily used by anyone, helps providing a better medical care in the neediest areas, such as quilombolas and indian communities or regions with poor medical infrastructure, enabling a prior identification of Glaucoma, thus favoring a better life quality for all population.

Membros:
- Luiz Souza (Universidade Federal de Pernambuco - Brazil)
- Luiz Oliveira Junior (Universidade Federal de Pernambuco - Brazil)
- Marcus Rios (Universidade Federal de Pernambuco - Brazil)
- Adriano Sarmento (UFPE - Brazil)

Automatic Interpreter of the Brazilian Sign Language

The goal of the Automatic Interpreter of the Brazilian Sign Language (IA-LIBRAS) is to ease the interaction of LIBRAS-dependent people with other persons.
There are not many studies concerning the automatic translation of LIBRAS to Portuguese, however as this processor involves capture and identification of these images, there are several studies involving the capture, processing and identification of images.
From these studies it can be seen that for best utilization and efficiency of identification of symbols, all articles converging in fact make a processing to normalize an image and delivering well characterized for final processing, wherein the comparison of the input image occurs input with values in a database and the symbol will be identified, after that individually identifies each symbol they are combined through dictionary libraries in order to obtain the words and phrases represented by the user. It was decided to use a DE2i-150 will use image recognition software to identify hand-made symbols representing letters of the alphabet or complete words. Images will be captured using a video camera, with the library computer vision (OpenCV) to do the processing of the images and use more of one type of identifying the images to increase the success rate of the system using area occupied by the region of interest after processing, separated into sub-sections and correlation of input images with a database of images.
 
Membros:
- Elton Broering (Instituto Federal de Santa Catarina - Brazil)
- Thiago Bonotto da Silva (Federal Institute of Education, Science and Technology of Santa Catarina - Brazil)
- Guilherme Evangelista de Albuquerque (Instituto Federal de Santa Catarina - Brazil)
- Arliones Hoeller Jr (Federal Institute for Education, Science and Technology of Santa Catarina - Brazil)

Guia Inteligente móvel para deficientes visuais

The everyday task of navigating one’s surrounding can amount to a true challenge to the visually impaired. Buildings are usually not designed with the challenges of this particular group of people in mind, which further aggravates the issue. Guide dogs have long been the most common attempt at solving this problem. However, guide dogs are quite limited, for they are incapable of reading signs and other visual clues which humans use naturally, and they can’t perform navigation, having to rely on their owners to also be a guide to them. Furthermore, the cost and effort involved in having a guide is often an issue, and the cost and time involved in training a guide dog means that one is not readily obtained. We aim to produce a system that is both lower in cost and richer in capabilities than the traditional solution to the problem, namely, guide dogs, while also being easier to obtain, and intend to achieve this via the recent advances in the processing power of embedded systems, the ease of access and use of a range of sensors, and the ubiquity of network connectivity. We propose our solution in the form a robotic car capable of guiding its user around buildings. The car is equipped with sensors that allow it to follow a path, avoid obstacles and determine when it has reached a destination. The system will be also capable of taking in voice commands, which in turn removes another barrier to the visually impaired.

Membros:
- Edna Barros (UFPE - Brazil)
- Lucas Barbosa (Centro de Informática - UFPE - Brazil)
- Ary Lins (Centro de Informática - UFPE - Brazil)
- Felipe Walmsley (Centro de Informática - UFPE - Brazil)

Sistema de detecção de obstáculos via eco localização.

O projeto consiste utilizar um sistema de localização de objetos a curta distân- cia por meio da reflexão de ondas sonoras em superfícies próximas.Dessa forma, imagi- na-se um ente móvel com finalidade de se localizar espacialmente sem a ajuda de câme- ras ou outros periféricos.

Membros:
- Lucas Coelho (Universidade Federal de Santa Catarina - Brazil)
- Vinícius Woyakewicz (Universidade Federal de Santa Catarina - Brazil)
- Viccenzo Benetti (Universidade Federal de Santa Catarina - Brazil)

Data Logger for the Public Transport (RodoMonitor)

A otimização no transporte público não inclui apenas uma melhor programação dos horários de circulação e das dimensões dos ônibus a serem utilizados em cada linha e período, mas também na elaboração de trajetos mais inteligentes. Atualmente, o Plano de Mobilidade Urbana Sustentável da Grande Florianópolis (PLAMUS) está realizando um estudo minucioso, ainda que manual, para identificar os “gargalos” do transporte público na cidade de Florianópolis1 para então propor soluções no sistema viário da capital. Neste sentido, esta proposta visa desenvolver um sistema embarcado (RodoMonitor) com o objetivo de realizar esta coleta de dados de forma automatizada, inteligente e direcio- nada de dados no transporte público da cidade de Florianópolis em Santa Catarina. 

Membros:
- Erich Alves (Federal University of Santa Catarina - UFSC - Brazil)
- Antônio Silvestre (Universidade Federal de Santa Catarina - Brazil)
- Djones Lettnin (UFSC - Brazil)
- Amadeu Plácido Neto (Universidade Federal de Santa Catarina - Brazil)

Monitoring System for the Elderly Fall

O projeto consiste em monitorar queda de idosos em residências e ambientes críticos e propícios a quedas, através de câmeras, processamento e tratamento de imagens. Será identificado situações que indiquem movimentos de quedas e tombos. Após o reconhecimento e a interpretação da queda, serão enviadas notificações para os familiares, assim como para instituições de atendimento de emergência. As notificações serão via celular, e-mail e telefones residenciais e serão enviadas automaticamente e instantaneamente diante do reconhecimento da queda.

Membros:
- Yuri Robin (Universidade de São Paulo - Brazil)
- Larissa Zimmermann (University of Sao Paulo - Brazil)
- Nivaldo Bondança (University of São Paulo - Brazil)

Sistema de Identificação Biométrica de Indivíduos Através da Antropometria e do Caminhar Humano

Identifying individuals using biometric data is an important task in surveillance, authentication and even entertainment. This task is even more challenging when required to be performed without physical contact and at a distance. The most recent trend is the use of full-body measurements to perform passive identification. The measurement of body parts (anthropometry) and gait analysis are examples of techniques that leverage such approach. In this work, the Microsoft Kinect and its NUI Skeleton API are used to extract automatically a skeleton from the user or users standing in front of the sensor. Such automatic extraction has the potential to simplify the process of extracting useful anthropometric and gait features for biometric identification. Thus, as the DE2i-150 Development Kit contains a processor that operates at a frequency below the required one by the Kinect sensor, the gait data cannot be captured, just anthropometric attributes. However, anthropometric attributes are sufficient to gender identification, as we do in this work. The process work as follows: the Microsoft Kinect sensor is connected to the DE2i-150 Development Board and captures video footages from a person. This person has his/her anthropometric attributes captured and the Euclidian distance is calculated in order to take the measures for all main parts of the body. This information is processed by a neural network, which output indicates if it is a male or female person. A storefront is also part of the application and shows female or male products, depending on the gender identification system’s output.

Membros:
- Aline Tonini (Universidade Federal de Pelotas - Brazil)
- Livia Amaral (Federal University of Pelotas - Brazil)
- Virginia Andersson (Federal University of Pelotas - Brazil)
- Julio Mattos (Universidade Federal de Pelotas - Brazil)

Li-Fi connected Media Center

A placa fornecida pela Intel será utilizada como servidor multimídia para ambientes fechados, como residências. Este servidor guardará todos os dados de áudio, vídeo e afins e estará conectado às lâmpadas do ambiente, de forma a prover conteúdo aos clientes através de Li-Fi. Os clientes serão placas (como a Raspberry Pi) conectadas a dispositivos de reprodução (e.g. televisão, som) e a receptores Li-Fi, permitindo que um arquivo transmitido pelo servidor seja captável e reprodutível simultaneamente por todos os dispositivos, resultando em um baixo consumo energético total.

Membros:
- Antônio Augusto Fröhlich (Universidade Federal de Santa Catarina - Brazil)
- Davi Resner (UFSC - Brazil)
- Lucas Sousa (Universidade Federal de Santa Catarina - Brazil)
- William Scariot (UFSC - Brazil)

Project Annuit Walk - PAW

O Projeto PAW trata-se de um óculos inteligente para deficientes visuais com foco na detecção de obstáculos. A ideia principal é promover a inclusão social dessas pessoas, dando mais conforto e segurança na sua mobilidade. Nossa pretensão é trazer uma experiência de cidade mais acessível para uma melhora em sua qualidade de vida. Além disso, para usuários portadores de smartphones, pretendemos também coletar dados referentes a qualidade das ruas por onde passam, calcular o nível de acessibilidade dessas áreas e notificar os órgãos responsáveis com o objetivo de melhorar a acessibilidade da sua região.

Membros:
- Marcos Penha (FBV/Devry University Brasil - Brazil)
- Alvaro Maia (FBV/Devry University Brasil - Brazil)
- Jalingson Assis (FBV/Devry University Brasil - Brazil)

Equipamento para medição e caracterização de canais e ruídos PLC

Nowadays, further than the common usage of the PL channel (Power line channel) on electric power transmission, it can also be used to transmit data over the same structure. That data transmission is called PLC (Power line Communication). The PLC kind of communication inherit several issues due to the instability of the channel. The noise and the channel behavior, without treatment, disrupts the correct data transmission. Sometimes, the channel fading and the noise are so strong that the proper communication becomes infeasible. The SNR (Signal to Noise Ratio) is a parameter that can be used to analyze the channel behavior and capacity. The first version of i9Analytics is a set of software and hardware that is able to make the analysis of a PLC channel between 1.7 and 50 MHz considering the values of SNR. The project consists of two transceivers; the first one is an OFDM (Orthogonal Frequency Division Multiplex) communication system transmitter, implemented on a development kit DE2-115. The second is a receiver, implemented on the development kit Intel DE2-150i, that analyzes the signal fading and extract the channel parameters. The communications occurs in the PLC channel due to the front-end developed by the team. It has analogic/digital and digital/analogic converters, a gain chip to amplify or attenuate the transmitted and received signal and analogic filters to attenuate the power signal.

Membros:
- Fabrício Campos (Universidade Federal de Juiz de Fora - Brazil)
- Diogo Fernandes (Universidade Federal de Juiz de Fora - Brazil)
- Hugo Schettino (Universidade Federal de Juiz de Fora - Brazil)
- Thiago Paschoalin (Universidade Federal de Juiz de Fora - Brazil)