Medidas de deslocamento e vibrações através de imagens de câmeras digitais

Pós-graduação em Engenharia Mecânica - FEIS

Classificação de tábuas de madeira usando processamento de imagens digitais e aprendizado de máquina

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Avaliação de Técnicas de Interpolação de Imagens Digitais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Inserção e extração de marca d'água em imagens digitais usando a transformada wavelet

Pós-graduação em Engenharia Elétrica - FEIS

Detecção e restauração de áreas sombreadas em imagens digitais de alta resolução espacial

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Análise de formas planas em imagens digitais

Given the widespread use of computers, the visual pattern recognition task has been automated in order to address the huge amount of available digital images. Many applications use image processing techniques as well as feature extraction and visual pattern recognition algorithms in order to identify people, to make the disease diagnosis process easier, to classify objects, etc. based on digital images. Among the features that can be extracted and analyzed from images is the shape of objects or regions. In some cases, shape is the unique feature that can be extracted with a relatively high accuracy from the image. In this work we present some of most important shape analysis methods and compare their performance when applied on three well-known shape image databases. Finally, we propose the development of a new shape descriptor based on the Hough Transform.

Estimativa do número de frutos verdes em laranjeiras com o uso de imagens digitais

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Imagens digitais na análise do uso da terra de uma microbacia como subsídio ao desenvolvimento sustentável

The present work sought to discriminate, to map and to quantify the areas of soil use of the Stream Monte Belo watershed - Botucatu (SP), obtained by digitale images. The cartographic bases were the shart planialtimetric, edited by IBGE (1969) and the satellite images LANDSAT - 7, passages of 21/01/1999, 08/01/2003 and 23/10/2006. The Software Idrisi Andes 15.0 were used for conversion of the analogical information for digital and for determination of the vegetable coverings areas. The results allowed to verify that the SIG - IDRISI Andes 15.0 were efficient in the quantification of the areas with soil use and that the analysis of the data showed a cash progress of the areas of reforestations to the detriment of the areas of pastures, especially from 1999, 2003 to 2006, when the field areas were substituted by the forestry in his totality. In spite of that progress, the forest areas that you correspond to the Permanent Preservation Areas, They are considerably preserved. That result comes to the encounter of the tendency of expansion of the forestry, especially after the installation of cellulose industries in the area, what worsened the environmental problems originating from of the practice of the monoculture.

Imagens digitais aplicadas no estudo da análise multitemporal do uso e ocupação do solo numa microbacia

The knowledge of the soil occupation as for his nature, location, occurrence form, changes happened in certain periods, they are valuable for the programming of activities that you seek to the development agricultural, economical and social of the area. This work aimed at to identify and to quantify the soil occupation of Stream Petiço Watershed - Botucatu (SP), through the Geographical Information System IDRISI and data of sensor Landsat 5 TM of 09/06/97 and 23/08/2013. For the analysis of the results it was verified that the eucalyptus culture, due to existence of great reforestation companies in the watershed, together with the native forests they are predominant in the study area, the remaining of the area is occupied by pastures and soil prepared for the planting of agricultural cultures.

Calibração e validação de um método de medida da radiação solar global por meio de actinógrafos baseada em técnicas de processamento de imagens digitais

O objetivo do trabalho é desenvolver um sistema informático de digitalização e processamento de actinogramas baseado em técnicas de Processamento de Imagens Digitais e comparar com o sistema tradicional de medidas. Os actinogramas foram fornecidos pela Estação Meteorológica de Botucatu (FCA/UNESP). As análises preliminares indicam um desempenho satisfatório do software proposto, gerando medidas na mesma ordem de grandeza do método de referência para partição diária. O software proposto pertence a um projeto que se encontra ainda em andamento, onde rotinas de técnicas diversas continuam sendo implementadas no reconhecimento da curva de interesse para melhorar a qualidade do processamento das informações gráficas dos actinogramas. Os actinogramas estão em fase de digitalização para que o software possa ser testado com uma base de dados mais consistente, onde poderão ser identificados tendências temporais dos dados resultantes da aplicação das técnicas de Processamento de Imagens Digitais no monitoramento da radiação solar por actinógrafos.

Análise do descritor de padrões mapeados localmente em multiescala para classificação de textura em imagens digitais

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Segmentação de texturas em imagens digitais utilizando wavelets redundantes

Pós-graduação em Matematica Aplicada e Computacional - FCT

Morfologia matemática aplicada à detecção de sombras e nuvens em imagens de alta resolução

The spatial resolution improvement of orbital sensors has broadened considerably the applicability of their images in solving urban areas problems. But as the spatial resolution improves, the shadows become even a more serious problem especially when detailed information (under the shadows) is required. Besides those shadows caused by buildings and houses, clouds projected shadows are likely to occur. In this case there is information occlusion by the cloud in association with low illumination and contrast areas caused by the cloud shadow on the ground. Thus, it's important to use efficient methods to detect shadows and clouds areas in digital images taking in count that these areas care for especial processing. This paper proposes the application of Mathematical Morphology (MM) in shadow and clouds detection. Two parts of a panchromatic QuickBird image of Cuiab-MT urban area were used. The proposed method takes advantage of the fact that shadows (low intensity - dark areas) and clouds (high intensity - bright areas) represent the bottom and top, respectively, of the image as it is thought to be a topographic surface. This characteristic allowed MM area opening and closing operations to be applied to reduce or eliminate the bottom and top of the topographic surface.