Submitted by FABRICIO MESQUITA DE ARO null (farotransmidia@gmail.com) on 2016-12-14T14:39:43Z No. of bitstreams: 1 Distorções-Elásticas-no-Cinema-Digital-de-Alexandr-Sokurov.pdf: 4048829 bytes, checksum: 607a1b260496bee0c99b0555423dc805 (MD5) / Approved for entry into archive by Felipe Augusto Arakaki (arakaki@reitoria.unesp.br) on 2016-12-19T17:36:29Z (GMT) No. of bitstreams: 1 aro_fm_me_bauru.pdf: 4048829 bytes, checksum: 607a1b260496bee0c99b0555423dc805 (MD5) / Made available in DSpace on 2016-12-19T17:36:29Z (GMT). No. of bitstreams: 1 aro_fm_me_bauru.pdf: 4048829 bytes, checksum: 607a1b260496bee0c99b0555423dc805 (MD5) Previous issue date: 2016-10-27 / O presente trabalho pretende elucidar os mecanismos que negaram a perspectiva linear por meio da distorção da imagem no cinema de Alexandr Sokurov. A partir da teoria da Dobra de Deleuze e dos preceitos da Perspectiva Inversa de Pável Floriênski, serão analisadas obras pictóricas, que vão do Barroco, passando pela Bauhaus, chegando até Francis Bacon. Tais obras entrarão em sintonia com a filmografia de Sokurov utilizando o termo da “distorção elástica”, pressupondo um deslocamento não-espacial e temporal-não-linear através da análise fílmica e estética das obras. A adaptação de Fausto de Goethe realizada pelo cineasta russo em 2012, será o elemento condutor ao elucidar o trânsito imagético do suporte analógico para o digital e suas potencialidades estéticas de subversão à perspectiva linear. / The present work intends to elucidate the mechanisms that denied the linear perspective inherited from Ancient Greece and emphasized in the Renaissance period, to undergo the process of distortion of this mechanism of representation. From the theory of Deleuze's Dobra and the precepts of the Inverse Perspective of Pável Floriênski, will be analyzed pictorial works, ranging from the Baroque, passing by the Bauhaus, reaching Francis Bacon. Such works will be in tune with the filmmaking of the Russian filmmaker Alexandr Sokurov using the term "elastic distortion", presupposing a non-spatial and non-linear displacement through the filmic and aesthetic analysis of works. Goethe's Faust's adaptation by the Russian filmmaker in 2012 will be the driving element in elucidating the imaginary transit from analog to digital support and its aesthetic potential from subversion to linear perspective.

abstract: Object detection is an interesting computer vision area that is concerned with the detection of object instances belonging to specific classes of interest as well as the localization of these instances in images and/or videos. Object detection serves as a vital module in many computer vision based applications. This work focuses on the development of object detection methods that exhibit increased robustness to varying illuminations and image quality. In this work, two methods for robust object detection are presented. In the context of varying illumination, this work focuses on robust generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS) under varying illumination conditions. The highlight of the first method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). It is first shown that the angular distortion in the Inverse Perspective Mapping (IPM) domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. This information is used to generate object proposals. A novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction is also proposed. In the context of image quality, this work focuses on robust multiple-class object detection using deep neural networks for images with varying quality. The use of Generative Adversarial Networks (GANs) is proposed in a novel generative framework to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher object detection and classification accuracy compared to the existing approaches. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2020

This master´s thesis deals with depiction aplication of camera like sensitive element for assisting system of car. It was proposed, how find a road, a lane and a obstacle on roadways. Only one camera was aplication for it. Solution is realized by methods, that are based on color and gradient of image. It applies simple methods and methods with mathematical model. Result is sum of method and its test and comparing. Realization of my program is present at resume of this thesis.