Reconhecimento de faces 3D com Kinect

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Influence of mobility models in precision spray aided by wireless sensor networks

Precision Spray is a technique to increase performance of Precision Agriculture. This spray technique may be aided by a Wireless Sensor Network, however, for such approach, the communication between the agricultural input applicator vehicle and network is critical due to its proper functioning. Thus, this work analyzes how the number of nodes in a wireless sensor network, its type of distribution and different areas of scenario affects the performance of communication. We performed simulations to observe system's behavior changing to find the most fitted non-controlled mobility model to the system.

Organization model for mobile wireless sensor networks inspired in artificial bee colony

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Surface coverage in wireless sensor networks based on delaunay tetrahedralization

In this work is presented a new method for sensor deployment on 3D surfaces. The method was structured on different steps. The first one aimed discretizes the relief of interest with Delaunay algorithm. The tetrahedra and relative values (spatial coordinates of each vertex and faces) were input to construction of 3D Voronoi diagram. Each circumcenter was calculated as a candidate position for a sensor node: the corresponding circular coverage area was calculated based on a radius r. The r value can be adjusted to simulate different kinds of sensors. The Dijkstra algorithm and a selection method were applied to eliminate candidate positions with overlapped coverage areas or beyond of surface of interest. Performance evaluations measures were defined using coverage area and communication as criteria. The results were relevant, once the mean coverage rate achieved on three different surfaces were among 91% and 100%.

Comparative gas sensor response of SnO2, SnO and Sn3O4 nanobelts to NO2 and potential interferents

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Sensitive luminescent paper-based sensor for the determination of gaseous hydrogen sulfide

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Design and implementation of wireless sensor networks for impedance-based structural health monitoring using ZigBee and Global System for Mobile Communications

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Ozone and nitrogen dioxide gas sensor based on a nanostructured SrTi0.85Fe0.15O3 thin film

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

The benefits of soft sensor and multi-rate control for the implementation of wireless networked control systems

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Geometrical parameter analysis of a high-sensitivity fiber optic angular displacement sensor

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Integration of wireless sensor networks to the internet of things using a 6LoWPAN Gateway

The Internet of Things is a new paradigm where smart embedded devices and systems are connected to the Internet. In this context, Wireless Sensor Networks (WSN) are becoming an important alternative for sensing and actuating critical applications like industrial automation, remote patient monitoring and domotics. The IEEE 802.15.4 protocol has been adopted as a standard for WSN and the 6LoWPAN protocol has been proposed to overcome the challenges of integrating WSN and Internet protocols. In this paper, the mechanisms of header compression and fragmentation of IPv6 datagrams proposed in the 6LoWPAN standard were evaluated through field experiments using a gateway prototype and IEEE 802.15.4 nodes.

Ultrasonic sensor signals and optimum path forest classifier for the microstructural characterization of thermally-aged inconel 625 alloy

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Monitoring a CuO gas sensor at work: an advanced in situ X-ray absorption spectroscopy study

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Classification of handwriting patterns in patients with Parkinson´s disease, using a biometric sensor

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Avaliação de desenpenho do método 3DLBP utilizando mapas de profundidade gerados pelo Microsoft Kinect

Problemas com pose e iluminação são desafios complexos para o reconhecimento de faces 2D. Devido a estes problemas vários métodos para reconhecimento de faces 3D têm sido propostos, principalmente pelo fato que os dados em 3D são mais resistentes a iluminação e são úteis para correção de pose. O maior problema com a utilização de métodos 3D é o custo elevado dos scanners 3D tradicionais. Uma alternativa é a utilização do Microsoft Kinect que, além de ser consideravelmente mais barato, é capaz de capturar os dados de profundidade com precisão necessária para discriminar sujeitos. O principal objetivo do presente trabalho é avaliar a performance do método 3DLBP para o reconhecimento de faces quando utilizando os mapas de profundidade gerados pelo Kinect. Outro objetivo é investigar quais regiões da face que desempenham melhor no reconhecimento de face.