Seleção de features guiada por atenção visual em imagens com fóvea

Visual attention is a very important task in autonomous robotics, but, because of its complexity, the processing time required is significant. We propose an architecture for feature selection using foveated images that is guided by visual attention tasks and that reduces the processing time required to perform these tasks. Our system can be applied in bottom-up or top-down visual attention. The foveated model determines which scales are to be used on the feature extraction algorithm. The system is able to discard features that are not extremely necessary for the tasks, thus, reducing the processing time. If the fovea is correctly placed, then it is possible to reduce the processing time without compromising the quality of the tasks outputs. The distance of the fovea from the object is also analyzed. If the visual system loses the tracking in top-down attention, basic strategies of fovea placement can be applied. Experiments have shown that it is possible to reduce up to 60% the processing time with this approach. To validate the method, we tested it with the feature algorithm known as Speeded Up Robust Features (SURF), one of the most efficient approaches for feature extraction. With the proposed architecture, we can accomplish real time requirements of robotics vision, mainly to be applied in autonomous robotics

Otimização de superfícies seletivas de frequência com elementos pré-fractais utilizando rede neural MLP e algoritmos de busca populacional

This thesis describes design methodologies for frequency selective surfaces (FSSs) composed of periodic arrays of pre-fractals metallic patches on single-layer dielectrics (FR4, RT/duroid). Shapes presented by Sierpinski island and T fractal geometries are exploited to the simple design of efficient band-stop spatial filters with applications in the range of microwaves. Initial results are discussed in terms of the electromagnetic effect resulting from the variation of parameters such as, fractal iteration number (or fractal level), fractal iteration factor, and periodicity of FSS, depending on the used pre-fractal element (Sierpinski island or T fractal). The transmission properties of these proposed periodic arrays are investigated through simulations performed by Ansoft DesignerTM and Ansoft HFSSTM commercial softwares that run full-wave methods. To validate the employed methodology, FSS prototypes are selected for fabrication and measurement. The obtained results point to interesting features for FSS spatial filters: compactness, with high values of frequency compression factor; as well as stable frequency responses at oblique incidence of plane waves. This thesis also approaches, as it main focus, the application of an alternative electromagnetic (EM) optimization technique for analysis and synthesis of FSSs with fractal motifs. In application examples of this technique, Vicsek and Sierpinski pre-fractal elements are used in the optimal design of FSS structures. Based on computational intelligence tools, the proposed technique overcomes the high computational cost associated to the full-wave parametric analyzes. To this end, fast and accurate multilayer perceptron (MLP) neural network models are developed using different parameters as design input variables. These neural network models aim to calculate the cost function in the iterations of population-based search algorithms. Continuous genetic algorithm (GA), particle swarm optimization (PSO), and bees algorithm (BA) are used for FSSs optimization with specific resonant frequency and bandwidth. The performance of these algorithms is compared in terms of computational cost and numerical convergence. Consistent results can be verified by the excellent agreement obtained between simulations and measurements related to FSS prototypes built with a given fractal iteration

Técnicas de computação natural para segmentação de imagens médicas

Image segmentation is one of the image processing problems that deserves special attention from the scientific community. This work studies unsupervised methods to clustering and pattern recognition applicable to medical image segmentation. Natural Computing based methods have shown very attractive in such tasks and are studied here as a way to verify it's applicability in medical image segmentation. This work treats to implement the following methods: GKA (Genetic K-means Algorithm), GFCMA (Genetic FCM Algorithm), PSOKA (PSO and K-means based Clustering Algorithm) and PSOFCM (PSO and FCM based Clustering Algorithm). Besides, as a way to evaluate the results given by the algorithms, clustering validity indexes are used as quantitative measure. Visual and qualitative evaluations are realized also, mainly using data given by the BrainWeb brain simulator as ground truth

Cadeia produtiva da nêspera na região do alto Tietê: indicadores econômicos da produção e mercado atacadista

A região do Alto Tietê é responsável por 85% da produção de nêspera do Estado de São Paulo. Atividade rentável, nos últimos anos os produtores verificaram uma queda na sua lucratividade. Este trabalho teve como objetivos sistematizar informações econômicas sobre a cadeia produtiva e analisar a estrutura de mercado. A evolução dos preços da nêspera mostra crescimento até o ano 2000 e posterior queda. O mercado atacadista tem atuado como um colchão amortecedor. O maior desafio para os produtores de nêspera se encontra no âmbito organizacional. A estrutura de mercado e os resultados da pesquisa de campo indicam que os produtores do Alto Tietê encontram-se em posição vantajosa para um reposicionamento nesse aspecto, importante para uma participação sustentável na atividade.

Odometria visual baseada em técnicas de structure from motion

Visual Odometry is the process that estimates camera position and orientation based solely on images and in features (projections of visual landmarks present in the scene) extraced from them. With the increasing advance of Computer Vision algorithms and computer processing power, the subarea known as Structure from Motion (SFM) started to supply mathematical tools composing localization systems for robotics and Augmented Reality applications, in contrast with its initial purpose of being used in inherently offline solutions aiming 3D reconstruction and image based modelling. In that way, this work proposes a pipeline to obtain relative position featuring a previously calibrated camera as positional sensor and based entirely on models and algorithms from SFM. Techniques usually applied in camera localization systems such as Kalman filters and particle filters are not used, making unnecessary additional information like probabilistic models for camera state transition. Experiments assessing both 3D reconstruction quality and camera position estimated by the system were performed, in which image sequences captured in reallistic scenarios were processed and compared to localization data gathered from a mobile robotic platform

Análise do efeito do tempo da moagem de alta energia no tamanho de cristalito e microdeformação da rede cristalina do WC-Co

Hard metals are the composite developed in 1923 by Karl Schröter, with wide application because high hardness, wear resistance and toughness. It is compound by a brittle phase WC and a ductile phase Co. Mechanical properties of hardmetals are strongly dependent on the microstructure of the WC Co, and additionally affected by the microstructure of WC powders before sintering. An important feature is that the toughness and the hardness increase simultaneously with the refining of WC. Therefore, development of nanostructured WC Co hardmetal has been extensively studied. There are many methods to manufacture WC-Co hard metals, including spraying conversion process, co-precipitation, displacement reaction process, mechanochemical synthesis and high energy ball milling. High energy ball milling is a simple and efficient way of manufacturing the fine powder with nanostructure. In this process, the continuous impacts on the powders promote pronounced changes and the brittle phase is refined until nanometric scale, bring into ductile matrix, and this ductile phase is deformed, re-welded and hardened. The goal of this work was investigate the effects of highenergy milling time in the micro structural changes in the WC-Co particulate composite, particularly in the refinement of the crystallite size and lattice strain. The starting powders were WC (average particle size D50 0.87 μm) supplied by Wolfram, Berglau-u. Hutten - GMBH and Co (average particle size D50 0.93 μm) supplied by H.C.Starck. Mixing 90% WC and 10% Co in planetary ball milling at 2, 10, 20, 50, 70, 100 and 150 hours, BPR 15:1, 400 rpm. The starting powders and the milled particulate composite samples were characterized by X-ray Diffraction (XRD) and Scanning Electron Microscopy (SEM) to identify phases and morphology. The crystallite size and lattice strain were measured by Rietveld s method. This procedure allowed obtaining more precise information about the influence of each one in the microstructure. The results show that high energy milling is efficient manufacturing process of WC-Co composite, and the milling time have great influence in the microstructure of the final particles, crushing and dispersing the finely WC nanometric order in the Co particles

Estudo da formulação de massas cerâmicas provenientes da região do Seridó-RN para fabricação de telhas

This work has for objective study compared the characteristics and technological properties of ceramic bodies from the region of Seridó-RN. The region under study has identified 23 cities where they were 80 ceramics industries. To define the universe of search, there was a survey of pottery that are part of APL Seridó next to the IEL. The characteristics and operating conditions of ceramics industries of the region were identified through a socio-economic questionnaire applied locally, which addressed issues such as: profiles of companies, production process etc. The analysis of information collected from 24 companies identified in seven cities shows that the vast majority of industries is small, with family structure, obsolete equipment and labo, little qualified. Most of the pottery works with low technical knowledge, poor control of the production process and product technology. The raw collected were submitted to analysis of X ray diffraction, chemical composition, termical analysis, particle size distribution and plasticity. Then were produced five formulations and made by uniaxial pressure at 25 MPa for firing in temperatures varying from 850 to 1050 °C. The firing technological properties evaluated were: mass loss to fire, lineal shrinkage, apparent density, apparent porosity, water absorption and flexural strength (3 points). The results indicated that the raw materials from the region have significant similarities in the composition chemical and mineralogical. Furthermore, it indicates the possibility of the use of cycles of firing faster and efficient than the current, limited to some clay mass burning of certain conditions

Obtenção de compósitos cerâmicos baseados em Al2O3/TiC através dos precursores poliméricos

The obtaining of ceramic materials from polymeric precursors is subject of numerous studies due to lower energy costs compared to conventional processing. The aim of this study is to investigate and improve the mechanism for obtaining ceramic matrix composite (CMC) based on SiOC/Al2O3/TiC by pyrolysis of polysiloxane in the presence of an active filler and inert filler in the pyrolysis temperature lower than the usually adopted for this technique, with greater strength. It also investigates the influence of pyrolysis temperature, the content of Alas active filler, the presence of infiltrating agents (Al, glass and polymer) after pyrolysis, temperature and infiltration time on some physical and mechanical properties. Alumina is used as inert filler and Al and Ti as active filler in the pyrolysis. Aluminum, glass and polysiloxane are used as agents infiltrating the post-pyrolysis. The results are analyzed with respect to porosity and bulk density by the Archimedes method, the presence of crystalline phases by X-ray diffraction (XRD) and microstructure by scanning electron microscopy (SEM). The ceramic pyrolyzed between 850 °C 1400 °C contain porosity 15% to 33%, density 2.34 g/cm3 and flexural strength at 4 points from 30 to 42 MPa. The microstructure features are porous, with an array of Al2O3 reinforced by TiC particles and AlTi3. The infiltration post-pyrolysis reveals decrease in porosity and increase density and strength. The composites have potential applications where thermal stability is the main requirement

Caracterização de matérias-primas regionais e desenvolvimento de formulações de massas cerâmicas para porcelanato

Initially concentrated in some poles at the South and Southeast regions of Brazil, the ceramic tiles industry became wide during the 80 s decade, with a disconcentration industrial and regional pulverization. The competitiveness in the ceramic tiles internal and external consumers markets, it has debtor the industries to invest in sophisticated products each time more, either in design or the technology, but, mainly, in its final properties. Amongst the diverse types of ceramic coating, the porcelanato if has detached had to its process of technological production and excellent characteristics techniques. The Porcelanato is currently the material for coatings that presents the best technical and aesthetic features when compared with others ceramics found on the market. The chemical composition and the others raw materials characteristics have an importance that must to be ally to the inherent characteristics of fabrication process, essentially those related to the cycle of burning. This work had as purpose to develop formularizations of ceramic mass for production of porcelanato without glass coating, pertaining to the group BIa (text of absorption of water ≤ 0.5%) and with resistance superior mechanics 35MPa from raw materials characterized. The ceramic raw materials selected to the development of this study (A1 and A2 clays, feldspate, talc and quartz) were submitted to the following tests: X-ray fluorescence - chemical analysis determination; X-ray diffraction - Analysis of the stages mineralogics; Laser granulometry - size distribution of particles; and Differential thermal analysis - thermal behavior. Were performed tests of absorption of water, lineal retraction of it burns, apparent specific mass and rupture tension the flexing. The results had evidenced that the formularizations that had the A1 clay and talc on its composition were efficient for the porcelanato production remaining their technological characteristics inside of the intervals of variation desired by the Norms of the ABNT