No description available.

A new design methodology that produces hardware solutions for performing real-time image processing is presented here. This design methodology provides significant advantages over traditional hardware design approaches by translating real-time image processing tasks into the gate-level resources of programmable logic-based hardware architectures. The use of programmable logic allows high-performance solutions to be realized with very efficient utilization of available logic and interconnection resources. These implementations provide comparable performance at a lower cost than other available programmable logic-based hardware architectures. This new design methodology is based on two components: a programmable logic-based destination hardware architecture and a suite of development system software. The destination hardware architecture is a Custom Computing Machine (CCM) that contains multiple Field Programmable Gate Array (FPGA) chips. FPGA chips provide gate-level programmability for the hardware architecture. Sophisticated software development tools, called the TRAVERSE development system software, are created to overcome the significant amount of time and expertise required to manually utilize this gate-level programmability. The new hardware architecture and development system software combine to establish a unique design methodology. There are several distinct contributions provided by this dissertation. The new flexible MORRPH hardware architecture provides a more efficient solution for creating real-time image processing computing machines than current commercial hardware architectures. The TRAVERSE development system software is the first integrated development system specifically for creating real-time image processing designs with multiple FPGA-based CCMs. New standards and design conventions are defined specifically for creating solutions to low-level image processing tasks, using the MORRPH architecture for verification. The circuit partitioning and global routing programs of the TRAVERSE development system software enable automated translation of image processing designs into the resources of multiple FPGA chips in the hardware architecture. In a broad sense, the individual contributions of this dissertation combine to create a new design methodology that will change the way hardware solutions are created for real-time image processing in the future. / Ph. D.

Podemos afirmar que deslocamentos da imagem em quadros consecutivos de uma seqüência de vídeo são causados por pequenas vibrações da câmera e/ou movimentos desejados pelo operador da câmera. A estabilização de imagem consiste no processo de remoção de pequenas vibrações que caracterizam movimentos indesejados de uma seqüência de imagens. Com este propósito, atualmente técnicas de processamento digital de vídeo vêm sendo comumente aplicadas na indústria eletrônica. No processo digital de estabilização de imagens são necessários métodos computacionais de estimação, de suavização e de correção de movimento, para os quais, existe uma grande variedade de técnicas de processamento. O emprego de uma técnica específica de processamento é determinado conforme o tipo de aplicação. Técnicas para a estimação de movimento como casamento de blocos (CB), e para a suavização de movimento como filtro de freqüência passa baixa, são freqüentemente encontradas na literatura. Este trabalho apresenta um sistema de estabilização digital de imagens em tempo real capturadas por uma câmera digital, estimando e compensando movimentos translacionais e rotacionais indesejados. / Undesirable shakes or jiggles, object motion within image or desirable motions caused by the camera operator causes image differences in consecutive frames of video sequences. The image stabilization consists of the process of removing inevitable and undesirable fluctuations, shakes and jiggles; with this purpose, nowadays digital processing techniques have been commonly applied in the electronic industry. On the digital processing of image stabilization, computational methods of estimation, smoothing and motion correction are necessary. In the literature various digital processing techniques for image stabilization are described, the most suitable technique should be chosen according to the kind of application. Techniques such as block matching used in motion estimation and low-pass filters used in motion smoothing are found in a great number of papers. This work presents a real time digital image stabilization system capable of stabilizing video sequences with undesirable translational and rotational displacements between frames.

Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2018-08-02T13:43:00Z No. of bitstreams: 1 Fernando Beretta Del Corona_.pdf: 4050624 bytes, checksum: 799d20c962674faef9e36c063091e725 (MD5) / Made available in DSpace on 2018-08-02T13:43:00Z (GMT). No. of bitstreams: 1 Fernando Beretta Del Corona_.pdf: 4050624 bytes, checksum: 799d20c962674faef9e36c063091e725 (MD5) Previous issue date: 2018-03-28 / Nenhuma / Esta pesquisa buscou compreender como se dá a construção do quadro cinematográfico dentro da obra da cineasta norte-americana Sofia Coppola a partir da análise de cinco de seus filmes: As virgens suicidas (1999), Encontros e desencontros (2003), Maria Antonieta (2006), Um lugar qualquer (2010) e Bling Ring: a gangue de Hollywood (2013). Para esse fim, se produziu um percurso histórico do cinema moderno na Europa e nos Estados Unidos no século XX, assim como do cinema independente norte-americano, contextualizando a obra da diretora dentro do movimento indie dos anos 1990. A fundamentação teórica estruturou-se a partir de conceitos e de ideias de Gilles Deleuze, Henri Bergson e André Bazin sobre a imagem. O processo da análise se baseou na metodologia da cartografia e dissecação audiovisual, de Deleuze, Félix Guattari e Walter Benjamin, trabalhando com as imagens nos filmes de Coppola, buscando entender como elas interagem entre si e o sentido que exprimem por meio dos elementos dentro do quadro. Através da análise se compreendeu como Coppola utiliza elementos como o corpo feminino, o olhar dos personagens, a vagueação e molduras secundárias para refletir sobre a sociedade contemporânea onde essas imagens são produzidas. / This research tried to understand how the construction of the cinematic frame works within the movies of north-American director Sofia Coppola, through the analysis of five of her films: The virgin suicides (1999), Lost in translation (2003), Marie Antoinette (2006), Somewhere (2010) and The Bling Ring (2013). To this end, the history of modern cinema in Europe and the United States in the 20th century was researched, as well as the history of independent cinema in America, contextualizing the director’s work within the indie movement of the 1990s. Theoretical foundation was based on concepts and ideas developed by authors Gilles Deleuze, Henri Bergson and André Bazin about images. The analysis process was based on the cartography and audiovisual dissection methodologies, by Deleuze, Félix Guattari and Walter Benjamin, working the images in Coppola’s movies, trying to understand how the interact with themselves and the meaning the express through the elements in the frame. Through the analysis it was understood how Coppola utilizes elements such as the feminine body, the character’s gaze, wanderings and secondary framing to reflect on the contemporary society where these images are produced.

Podemos afirmar que deslocamentos da imagem em quadros consecutivos de uma seqüência de vídeo são causados por pequenas vibrações da câmera e/ou movimentos desejados pelo operador da câmera. A estabilização de imagem consiste no processo de remoção de pequenas vibrações que caracterizam movimentos indesejados de uma seqüência de imagens. Com este propósito, atualmente técnicas de processamento digital de vídeo vêm sendo comumente aplicadas na indústria eletrônica. No processo digital de estabilização de imagens são necessários métodos computacionais de estimação, de suavização e de correção de movimento, para os quais, existe uma grande variedade de técnicas de processamento. O emprego de uma técnica específica de processamento é determinado conforme o tipo de aplicação. Técnicas para a estimação de movimento como casamento de blocos (CB), e para a suavização de movimento como filtro de freqüência passa baixa, são freqüentemente encontradas na literatura. Este trabalho apresenta um sistema de estabilização digital de imagens em tempo real capturadas por uma câmera digital, estimando e compensando movimentos translacionais e rotacionais indesejados. / Undesirable shakes or jiggles, object motion within image or desirable motions caused by the camera operator causes image differences in consecutive frames of video sequences. The image stabilization consists of the process of removing inevitable and undesirable fluctuations, shakes and jiggles; with this purpose, nowadays digital processing techniques have been commonly applied in the electronic industry. On the digital processing of image stabilization, computational methods of estimation, smoothing and motion correction are necessary. In the literature various digital processing techniques for image stabilization are described, the most suitable technique should be chosen according to the kind of application. Techniques such as block matching used in motion estimation and low-pass filters used in motion smoothing are found in a great number of papers. This work presents a real time digital image stabilization system capable of stabilizing video sequences with undesirable translational and rotational displacements between frames.

At present, the quality of image taken from infrared cameras is low compared to the other cameras because of manufacturing technology. So, resolution enhancement processes are becoming more important for these cameras. Super resolution is a good approach to solve this resolution problem. In general, the systems that infrared cameras used require video processing to perform in real time. So, a suitable approach should be selected and implemented to work in real time. The computational load and processing time are big issues in this case. FPGAs are proven to be suitable hardware devices for these types of works. Super resolution involves two parts as global motion estimation and high resolution image reconstruction. In this study, one suitable algorithm, namely as PM, for global motion estimation in the literature is selected to be implemented in real time. On the other hand, for high resolution image reconstruction part, FPGA structures of some well known algorithms in the literature, namely as POCS, MLE, MAP and LMS are proposed and their performance, resource requirements and timing considerations are discussed. Most efficient one is selected and implemented in FPGA.

Optical flow is used in a number of computer vision applications. However, its use in mobile robotic applications is limited because of the high computational complexity involved and the limited availability of computational resources on such platforms. The lack of a hardware that is capable of computing optical flow vector field in real time is a factor that prevents the mobile robotics community to efficiently utilize some successful techniques presented in computer vision literature. In this thesis work, we design and implement a high performance FPGA hardware with a small footprint and low power consumption that is capable of providing over-realtime optical flow data and is hence suitable for this application domain. A well known differential optical flow algorithm presented by Horn &amp / Schunck is selected for this implementation. The complete hardware design of the proposed system is described in details. We also discuss the design alternatives and the selected approaches together with a discussion of the selection procedure. We present the performance analysis of the proposed hardware in terms of computation speed, power consumption and accuracy. The designed hardware is tested with some of the available test sequences that are frequently used for performance evaluations of the optical flow techniques in literature. The proposed hardware is capable of computing optical flow vector field on 256x256 pixels images in 3.89ms which corresponds to a processing speed of 257 fps. The results obtained from FPGA implementation are compared with a floating-point implementation of the same algorithm realized on a PC hardware. The obtained results show that the hardware implementation achieved a superior performance in terms of speed, power consumption and compactness while there is minimal loss of accuracy due to the fixed point implementation.

The objective of this study is to implement a low-cost smart camera application on a Commercial off the Shelf system that is based on Texas Instrument&rsquo / s DM3730 System on Chip processor. Although there are different architectures for smart camera applications, ARM plus DSP based System on Chip architecture is selected for implementation because of its different core abilities. Beagleboard-XM platform that has an ARM plus DSP based System on Chip processor is chosen as Commercial off the Shelf platform. During this thesis, firstly to start-up the Commercial off the Shelf platform the design steps of porting an embedded Linux to ARM core of System on Chip processor is described. Then design steps that are necessary for implementation of smart camera applications on both ARM and DSP cores in parallel are given in detail. Furthermore, the real-time image processing performance of the Beagleboard-xM platform for the smart camera applications is evaluated with simple implementations.

Gilles Deleuze'as kuria kinui būdingus konceptus, kurie pagilina kino problematiką, suteikdami jai filosofinį pagrindą. Savo vaizdinio-judėjimo ir vaizdinio-laiko knygose – Kinas 1 ir Kinas 2 – Deleuze'as konceptus taiko klasikiniui ir moderniajam kinui. Kino filmų jis nepasirenka kaip savo konceptų iliustracijų, o juos vertina kaip tuos pačius konceptus, išreikštus vaizdine forma. Pagrindinis šio magistrinio darbo tikslas – aptarti bet-kurios-erdvės, kuri priklauso vaizdinio-judėjimo kinui ir išreiškia netiesioginį laiką, ir vaizdo-kristalo, išreikšiantį sudėtingą tiesioginio laiko sistemą, konceptus ir tirti jų apraiškas kino mene. / Gilles Deleuze creates concepts characteristic of cinema which deepen the problematics of cinema providing a philosophical basis to it. In his books of movement-image and time-image – Cinema 1 and Cinema 2 – Deleuze applies concepts to classical and modern cinema. He doesn‘t choose movies as illustrations of his concepts but values them as the same concepts expressed in visual form. The main aim of this master thesis – to discuss the concepts of any-space-whatever, which belongs to the cinema of movement-image and expresses indirect time, as well as of crystal-image, which expresses a complex system of direct time, and to investigate their manifestations in the art of cinema.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2016-04-04T14:21:22Z No. of bitstreams: 1 tomyocostaito.pdf: 1770745 bytes, checksum: 7da766d3e43e9cd6f28664b22e9be58b (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2016-04-24T03:56:20Z (GMT) No. of bitstreams: 1 tomyocostaito.pdf: 1770745 bytes, checksum: 7da766d3e43e9cd6f28664b22e9be58b (MD5) / Made available in DSpace on 2016-04-24T03:56:20Z (GMT). No. of bitstreams: 1 tomyocostaito.pdf: 1770745 bytes, checksum: 7da766d3e43e9cd6f28664b22e9be58b (MD5) Previous issue date: 2013-03-26 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Esta pesquisa tenta mimetizar os modos de pensamento traçados pelas articulações das imagens e sons do filme Dez, de Abbas Kiarostami, a partir de um modelo ensaístico inspirado no método benjaminiano. Realizamos um mapeamento do conceito de mímesis de Walter Benjamin identificando pontos estratégicos para a construção de nosso ensaio. Apresentamos os dois grandes modos de pensamento do cinema segundo a classificação de Gilles Deleuze, explicitando suas diferenças: a imagem-movimento e a imagem-tempo. Descrevemos o modo de utilização das técnicas cinematográficas em Dez a partir das categorias de espaço de produção e de espaço fílmico. Analisamos as imagens de Dez, com base na descrição realizada anteriormente, evidenciando que o modo de pensamento engendrado pelas imagens corresponde ao da imagem-tempo, apontando o conceito de imagem-corpo como uma possível subcategoria. Ao final do trabalho, apresentamos nossa tentativa de mimetizar o modo de pensamento do filme a partir da imagem-corpo, buscando suscitar, no leitor, imagens, que, por meio da escrita, possam estabelecer uma configuração comum com o modo de pensar do filme. / This research tries to mimetize the modes of thought constructed by the images and sounds of the film Ten by Abbas Kiarostami through a model inspired by the essayistic method of Walter Benjamin. We conducted a mapping of the concept of mimesis in Benjamin‟s writings identifying strategic points for the construction of our own essay. We also work two major ways of thinking cinema according to the classification of Gilles Deleuze, explaining their differences: the movement-image and time-image. We describe the use of techniques in the film Ten with the help of the categories of production space and filmic space. We analyzed the images of Ten, based on the description previously performed, showing that the mode of thought engendered by the images corresponds to the time-image, showing the concept of body-image as a possible sub. At the end of the paper, we present our attempt to mimetize the mode of thought of the film through the concept of body-image, seeking to raise images through writing, with the goal of establishing a common configuration with the thinking of the movie.