Repository logo

ESTG - Mestrado em Engenharia Eletrotécnica

Permanent URI for this collection

http://hdl.handle.net/10400.8/5618

Browse

Browsing ESTG - Mestrado em Engenharia Eletrotécnica by advisor "Faria, Sérgio Manuel Maciel de"

Now showing 1 - 2 of 2
  • Efficient processing techniques for depth maps generated by rgb-d sensors
    Publication . Gama, Filipe Xavier da Graça; Rodrigues, Nuno Miguel Morais; Faria, Sérgio Manuel Maciel de
    Nesta dissertação, um novo método para melhorar mapas de profundidade gerados por sensores RGB-D como a Microsoft Kinect e a Asus Xtion Pro Live é apresentado. Mapas de profundidade gerados por sensores RGB-D normalmente contêm diversos artefactos como oclusões ou buracos devido aos erros de medição da profundidade e das propriedades da superfície dos objetos. Estes problemas têm no seu conjunto um impacto negativo em aplicações que dependem da qualidade dos mapas de profundidade. Neste trabalho, um novo método foi desenvolvido de modo a assegurar que os buracos são preenchidos, que os contornos dos objetos são bem definidos e alinhados com a imagem de textura. O método proposto combina a informação da segmentação da imagem de textura com o método de inpainting baseado nas equações de Navier-Stokes. Para além disso, o método proposto também integra um filtro não-linear para redução do ruído. Este filtro utiliza a informação da imagem de textura para o efeito. Testes experimentais mostram que o método proposto obtém a mesma performance de métodos da literatura atual em termos de qualidade do melhoramento de mapas de profundidade.
    2015-11-18Master thesis Restricted access Show more
  • Improved image rendering for focused plenoptic cameras with extended depth-of-field
    Publication . Filipe, José Nunes dos Santos; Távora, Luís Miguel Oliveira Pegado de Noronha e; Faria, Sérgio Manuel Maciel de
    This dissertation presents a research work on rendering images from light elds captured with a focused plenoptic camera with extended depth of eld. A basic overview of the 7 dimensional plenoptic function is rst given, followed by a description of the Two-Plane Parametrisation. Some of the various methods used for sampling the plenoptic functions are then described, namely those equivalent to acquisition functions implemented by the camera gantry, the unfocused plenoptic camera and the focused plenoptic camera. State-of-the-art image rendering algorithms have also been studied both for focused and unfocused plenoptic cameras. A comprehensive study of the behaviour of focus metrics when applied to images rendered form a focused plenoptic camera is presented, including 34 of the most widely used metrics in the literature. Due to high frequency artefacts, caused by the rendering process, it was found that the currently available focus metrics yield in ated values for this kind of images, leading to misindication, where worse-focused images have better focus measures. Subjective tests were carried out, in order to corroborate these results. Then, methods for minimizing the rendering artefacts are proposed. An algorithm for choosing the maximum patch size for each micro-image was designed, in order to minimize the distortions caused by the vignetting e ect of the micro-lens. Then an inpainting algorithm, based on anisotropic di usion inpainting, is used to minimize the remaining artefacts present in the borders between adjacent micro-images. Finally, a method to deal with the redundant information generated by a plenoptic camera with extended depth of eld is presented. Three di erent views of the same scene are rendered, with the three di erent types of lenses. Then, it is proven that making any linear combination of the images always results in worse focus than selecting the better focused one. Thus, a multi-focus image fusion algorithm is proposed to merge the three images captured by a extended depth-of- eld camera into a single one, which presents higher focus level than any of the three individual images.
    2019-02-05Master thesis Open access Show more