Paralelização de algoritmos de trimap utilizando a arquitetura Cuda

Techniques of image combination, with extraction of objects to set a final scene, are very used in applications from photos montages to cinematographic productions. These techniques are called digital matting. With them is possible to decrease the cost of productions, because it is not necessary for the actor to be filmed in the location where the final scene occurs. This feature also favors its use in programs made to digital television, which demands a high quality image. Many digital matting algorithms use markings done on the images, to demarcate what is the foreground, the background and the uncertainty areas. This marking is called trimap, which is a triple map containing these three informations. The trimap is done, typically, from manual markings. In this project, methods were created that can be used in digital matting algorithms, with restriction of time and without human interaction, that is, the creation of an algorithm that generates the trimap automatically. This last one can be generated from the difference between a color of an arbitrary background and the foreground, or by using a depth map. It was also created a matting method, based on the Geodesic Matting (BAI; SAPIRO, 2009), which has an inferior processing time then the original one. Aiming to improve the performance of the applications that generates the trimap and of the algorithms that generates the alphamap (map that associates a value to the transparency of each pixel of the image), allowing its use in applications with time restrictions, it was used the CUDA architecture. Taking advantage, this way, of the computational power and the features of the GPGPU, which is massively parallel

O aprimoramento de um software de estúdio virtual por meio de técnicas de matting digital e registro de objetos virtuais

A virtual studio system can use technologies as augmented reality and digital matting to decrease production costs at the same time it provides the same resources of a conventional studio. With this, it’s possible for the current studios, with low cost and using conventional devices, to create productions with greater image quality and effects. Some difficulties are recurrent in virtual studio applications that use augmented reality and digital matting. The virtual objects registration in augmented reality techniques suffer from problems caused by optical distortions in the camera, errors in the marker tracking system, lack of calibration on the equipments or on the environment (lighting, for example), or even by delays in the virtual objects display. On the other hand, the digital matting’s main problem is the real-time execution to preview the scene, which must have optimized processing speed at the same time while maintain the best image quality possible. Taking the given context into consideration, this work aims to give continuity to a virtual studio system called ARStudio, by enhancing digital matting, virtual objects registration and introducing a segmentation based on depth map, yet adding better control over functionalities previously implemented

Aplicação de sistemas imunológicos artificiais para biometria facial: Reconhecimento de identidade baseado nas características de padrões binários

Pós-graduação em Engenharia Elétrica - FEIS

The use of elevation map histograms for topographic heterogeneity analysis

Surface defects are extremely important in mechanical characterization of several different materials. Therefore, the analysis of surface finishing is essential for a further simulation of surface mechanical properties in a customized project in materials science and technology. One of the methods commonly employed for such purpose is the statistical mapping of different sample surface regions using the depth from focus technique. The analysis is usually performed directly from the elevation maps which are obtained from the digital image processing. In this paper, the possibility of quantifying the surface heterogeneity of Silicon Carbide porous ceramics by elevation map histograms is presented. The advantage of this technique is that it allows the qualitative or quantitative verification of all surface image fields that cannot be done by using the Surface Plot plugin of image J™ platform commonly used in digital image processing. © 2012 Springer Science+Business Media, LLC.

Spatial distribution of runoff depth from a watershed located in a cuesta relief area of São Paulo State, Brazil

This study was undertaken in a 1566 ha drainage basin situated in an area with cuesta relief in the state of São Paulo, Brazil. The objectives were: 1) to map the maximum potential soil water retention capacity, and 2) to simulate the depth of surface runoff in each geographical position of the area based on a typical rainfall event. The database required for the development of this research was generated in the environment of the geographical information system ArcInfo v.10.1. Undeformed soil samples were collected at 69 points. The ordinary kriging method was used in the interpolation of the values of soil density and maximum potential soil water retention capacity. The spherical model allowed for better adjustment of the semivariograms corresponding to the two soil attributes for the depth of 0 to 20 cm, while the Gaussian model enabled a better fit of the spatial behavior of the two variables for the depth of 20 to 40 cm. The simulation of the spatial distribution revealed a gradual increase in the depth of surface runoff for the rainfall event taken as example (25 mm) from the reverse to the peripheral depression of the cuesta (from west to east). There is a positive aspect observed in the gradient, since the sites of highest declivity, especially those at the front of the cuesta, are closer to the western boundary of the watershed where the lowest depths of runoff occur. This behavior, in conjunction with certain values of erodibility and depending on the land use and cover, can help mitigate the soil erosion processes in these areas.

Transfer function-noise modeling and spatial interpolation to evaluate the risk of extreme (shallow) water-table levels in the Brazilian Cerrados

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Spatial variability of soil penetration resistance influenced by season of sampling

O objetivo deste trabalho foi analizar a distribuição espacial da compactação do solo e a influência da umidade do solo na resistência à penetração. Esta última variável foi descrita pelo índice de cone. O solo estudado foi Nitossolo e os dados de índice de cone foram obtidos usando um penetrômetro. A resistência do solo foi avaliada a 5 profundidades diferentes, 0-10 cm, 10-20 cm, 20-30 cm, 30-40 cm e mais de 40 cm, porém o conteúdo de umidade do solo foi medido a 0-20 cm e 20-40 cm. As condições hídricas do solo variaram nas diferentes amostragems. Os coeficientes de variação para o índice de cone foram 16,5% a 45,8% e os do conteúdo de umidade do solo variaram entre 8,96% e 21,38%. Os resultados sugeriram elevada correlação entre a resistência do solo, estimada pelo índice de cone e a profundidade do solo. Sem embargo, a relação esperada com a umidade do solo não foi apreciada. Observou-se dependência espacial em 31 de 35 séries de dados de índice de cone e umidade do solo. Esta dependência foi ajustada por modelos exponenciais com efeito pepita variável de 0 a 90% o valor do patamar. em séries de dados o comportamento foi aleatório. Portanto, a técnica das distâncias inversas foi utilizada para cartografar a distribuição das variáveis que não tiveram estrutura espacial. Na krigagem constatou-se uma suavização dos mapas comparados com esses das distâncias inversas. A krigagem indicadora foi utilizada para cartografar a variabilidade espacial do índice de cone e recomendar melhor manejo do solo.

Desenvolvimento de equipamentos para o mapeamento de áreas infestadas por macrófitas aquáticas imersas

Foi desenvolvido um conjunto de equipamentos com o objetivo de mapear as áreas infestadas por macrófitas aquáticas, auxiliando operações de manejo mecânico, as quais são realizadas por uma colhedora desenvolvida especificamente para essa finalidade. O conjunto de equipamentos foi constituído por um GPS com programa de correção diferencial, acoplado a um palmtop, um sistema com dois teclados ligados em dataloggers e um transdutor de deslocamento linear LT. O GPS, através do palmtop, proporcionava o mapeamento da área de deslocamento, auxiliando o operador na movimentação da máquina, otimizando a operação e evitando, dessa forma, a sobreposição das faixas de coleta na área a ser manejada. Um dos teclados monitorava a movimentação e operação da colhedora, além da presença de obstáculos, como tocos e bancos de areia, enquanto o outro gerava dados sobre a presença de determinada espécie de planta, como E. densa, E. najas e C. demersum, além do nível de infestação destas plantas. O transdutor, instalado na plataforma frontal da colhedora, se movimentava linearmente, gerando informações sobre a profundidade da coleta realizada. Dessa forma, pôde-se observar que o desenvolvimento desse conjunto de equipamentos foi de grande utilidade e auxiliou a operação de controle mecânico de áreas infestadas por macrófitas aquáticas imersas, possibilitando, assim, o planejamento de operações de manejo e controle subseqüentes.

3-D reconstruction by extended depth-of-field in failure analysis - Case study II: Fractal analysis of interlaminar fracture in carbon/epoxy composites

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

Extended depth from focus reconstruction using NIH ImageJ plugins: Quality and resolution of elevation maps

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

MRT letter: Extended depth from focus reconstruction method for stretch zone measurement in 15-5PH steel

The stretch zone width (SZW) data for 15-5PH steel CTOD specimens fractured at -150 degrees C to + 23 degrees C temperature were measured based on focused images and 3D maps obtained by extended depth-of-field reconstruction from light microscopy (LM) image stacks. This LM-based method, with a larger lateral resolution, seems to be as effective for quantitative analysis of SZW as scanning electron microscopy (SEM) or confocal scanning laser microscopy (CSLM), permitting to clearly identify stretch zone boundaries. Despite the worst sharpness of focused images, a robust linear correlation was established to fracture toughness (KC) and SZW data for the 15-5PH steel tested specimens, measured at their center region. The method is an alternative to evaluate the boundaries of stretched zones, at a lower cost of implementation and training, since topographic data from elevation maps can be associated with reconstructed image, which summarizes the original contrast and brightness information. Finally, the extended depth-of-field method is presented here as a valuable tool for failure analysis, as a cheaper alternative to investigate rough surfaces or fracture, compared to scanning electron or confocal light microscopes. Microsc. Res. Tech. 75:11551158, 2012. (C) 2012 Wiley Periodicals, Inc.

3-D reconstruction by extended depth-of-field in failure analysis - Case study I: Qualitative fractographic investigation of fractured bolts in a partial valve

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

Structural depth profile and nanoscale piezoelectric properties of randomly oriented Pb(Zr0.50Ti0.50)O-3 thin films

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

Variabilidade espacial de atributos da fertilidade de um Latossolo Vermelho Distroférrico sob Sistema Plantio Direto

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Use of bispectral index to monitor depth of anesthesia in isoflurane-anesthetized dogs

Objective-To evaluate the correlation between the bispectral index (BIS) and end-tidal isoflurane (ETISO) concentration and compare the use of 3 BIS sensor positions in dogs.Animals-6 adult dogs.Procedures-Mechanically ventilated dogs received pancuronium, and depth of anesthesia was altered by increasing ETISO concentration from 1.5% to 2.3% and 3.0%. The BIS, suppression ratio (relative percentage of isoelectric electroencephalographic waveforms), and signal quality index (SQI) were recorded at each ET, so concentration for each of 3 BIS sensor positions (frontal-occipital, bifrontal, and frontal-temporal positions).Results-The BIS and ETISO concentration were poorly correlated-, regardless of sensor positioning, mean BIS values did not change significantly as ETISO was increased. At 3% isoflurane, regardless of sensor positioning, there was an increase in suppression ratio coincident with BIS < 40 in some dogs, whereas paradoxic increases in BIS (> 60) were recorded in others. Furthermore, at 3.0% isoflurane, the SQI was significantly lower for the bifrontal sensor position (compared with values for the other positions), but low SQI values prevented recording of BIS values from the frontal-occipital sensor position in 2 dogs. Overall, BIS values derived from the 3 sensor positions did not differ.Conclusions and Clinical Relevance-In dogs, BIS values may not reflect changes in depth of isoflurane anesthesia in the absence of noxious stimulation. of the 3 sensor positions, frontal-temporal positioning provided better correlation with changes in depth of anesthesia induced via changes in isoflurane concentrations. However, the sensor placements yielded similar results at SQI values > 50.