Uma proposta metodológica de integração de técnicas de análise espectral e de inteligência computacional, baseadas em conhecimento, para o reconhecimento de padrões em imagens multiespectrais

Somente no ano de 2011 foram adquiridos mais de 1.000TB de novos registros digitais de imagem advindos de Sensoriamento Remoto orbital. Tal gama de registros, que possui uma progressão geométrica crescente, é adicionada, anualmente, a incrível e extraordinária massa de dados de imagens orbitais já existentes da superfície da Terra (adquiridos desde a década de 70 do século passado). Esta quantidade maciça de registros, onde a grande maioria sequer foi processada, requer ferramentas computacionais que permitam o reconhecimento automático de padrões de imagem desejados, de modo a permitir a extração dos objetos geográficos e de alvos de interesse, de forma mais rápida e concisa. A proposta de tal reconhecimento ser realizado automaticamente por meio da integração de técnicas de Análise Espectral e de Inteligência Computacional com base no Conhecimento adquirido por especialista em imagem foi implementada na forma de um integrador com base nas técnicas de Redes Neurais Computacionais (ou Artificiais) (através do Mapa de Características Auto- Organizáveis de Kohonen SOFM) e de Lógica Difusa ou Fuzzy (através de Mamdani). Estas foram aplicadas às assinaturas espectrais de cada padrão de interesse, formadas pelos níveis de quantização ou níveis de cinza do respectivo padrão em cada uma das bandas espectrais, de forma que a classificação dos padrões irá depender, de forma indissociável, da correlação das assinaturas espectrais nas seis bandas do sensor, tal qual o trabalho dos especialistas em imagens. Foram utilizadas as bandas 1 a 5 e 7 do satélite LANDSAT-5 para a determinação de cinco classes/alvos de interesse da cobertura e ocupação terrestre em três recortes da área-teste, situados no Estado do Rio de Janeiro (Guaratiba, Mangaratiba e Magé) nesta integração, com confrontação dos resultados obtidos com aqueles derivados da interpretação da especialista em imagens, a qual foi corroborada através de verificação da verdade terrestre. Houve também a comparação dos resultados obtidos no integrador com dois sistemas computacionais comerciais (IDRISI Taiga e ENVI 4.8), no que tange a qualidade da classificação (índice Kappa) e tempo de resposta. O integrador, com classificações híbridas (supervisionadas e não supervisionadas) em sua implementação, provou ser eficaz no reconhecimento automático (não supervisionado) de padrões multiespectrais e no aprendizado destes padrões, pois para cada uma das entradas dos recortes da área-teste, menor foi o aprendizado necessário para sua classificação alcançar um acerto médio final de 87%, frente às classificações da especialista em imagem. A sua eficácia também foi comprovada frente aos sistemas computacionais testados, com índice Kappa médio de 0,86.

Computer simulation of intrinsic defects in YAlO3 single crystal

National Nature Science Foundation of China (Grant No. 60607015)

Simulation stochastique des structures démographiques. Application aux populations d'albacores, Thunnus albacares

A computer program has been written in order to generate a population of fishes following a Von Bertalanffy growth curve with a random Gaussian variability for birth dates and growth parameters K and L ∞. Standard deviations for these 3 parameters are chosen separately for each run. Fishing and natural mortalities are applied to this population. Using as an input parameters usually taken for yellowfin in the eastern Atlantic, the simulation suggests a standard deviation between 1 and 2 months for the birth dates in this population. It also indicates that increasing levels of fishing mortalities must produce a better agreement between age and length for the larger fish.

Fish tracking technology development. Phases 1 and 2, project definition desk study and equipment

The document reports on the major findings from a definition study to appraise the options to develop fish tracking equipment, in particular tags and data logging systems, in order to improve the effeciency of the Agency tracking studies and to obtain a greater understanding of fish biology. The definition study was in two parts. The first, Phase 1, collated and evaluated all the known tracking systems that may be suitable for studies of fish which are either produced commercially or have been constructed for specific in-house studies. Phase 2 was an evaluation of all the tracking equipment considered to merit further investigation in Phase 1. The deficiencies between existing and required technologies to improve the efficiency of Agency's tracking studies and to obtain a greater understanding of fish biology are also identified.

An investigation into the effects of electric fishing equipment on salmon and sea trout within the area of the Lancashire River Board.

The report looks at experiments into electric fishing equipment and effects on salmon and trout within the Lancashire River Board. Experiments include obtaining information on voltage gradients, ascertaining what damage to fish of the larger size groups resulted from electric fishing, determining whether or not fractures could occur in coarse fish and brown trout,similar to those occurring in salmon and sea trout, and effects low temperatures have on electrofishing techniques.

Linear Chromatic Adaptation Transform Based on Delaunay Triangulation

Computer vision algorithms that use color information require color constant images to operate correctly. Color constancy of the images is usually achieved in two steps: first the illuminant is detected and then image is transformed with the chromatic adaptation transform ( CAT). Existing CAT methods use a single transformation matrix for all the colors of the input image. The method proposed in this paper requires multiple corresponding color pairs between source and target illuminants given by patches of the Macbeth color checker. It uses Delaunay triangulation to divide the color gamut of the input image into small triangles. Each color of the input image is associated with the triangle containing the color point and transformed with a full linear model associated with the triangle. Full linear model is used because diagonal models are known to be inaccurate if channel color matching functions do not have narrow peaks. Objective evaluation showed that the proposed method outperforms existing CAT methods by more than 21%; that is, it performs statistically significantly better than other existing methods.

A computer software package for assessing and managing risks posed by experiments with genetically modified fish and shellfish

Assessment and management of risk is needed for sustainable use of genetically modified aquatic organisms (aquatic GMOs). A computer software package for safely conducting research with genetically modified fish and shellfish is described. By answering a series of questions about the organism and the accessible aquatic ecosystem, a researcher or oversight authority can either identify specific risks or conclude that there is a specific reason for safety of the experiment. Risk assessment protocols with examples involving transgenic coho salmon, triploid grass carp and hybrid tilapia are described. In case a specific risk is identified, the user is led to consider risk management measures, involving culture methods, facilities design and operations management, to minimize the risk. Key features of the software are its user-friendly organization; easy access to explanatory text, literature citations and glossary; and automated completion of a worksheet. Documented completion of the Performance Standards can facilitate approval of a well designed experiment by oversight authorities.