In this thesis, we propose a chroma keying system that automatically estimates the alpha map and the reliable intrinsic color of foreground objects in front of solid background. Our system is designed to be capable of distinguishing the transparent foreground from the re flective foreground and shaded background, thereby making the artifacts of the composited image less conspicuous. Speci cally, we assume that the transparent region tends to be with higher saturation and lightness compared with region re ecting background light. With this assumption, a threshold function (TF) on a saturation-lightness plane is de ned according to human visual experiments. The pixels with color mixed with the background light (conventional unknown pixels) are now further categorized into re ective pixels and transparent pixels according to TF. In this case, the re ective and the transparent regions are separated to improve the alpha matte quality. Furthermore, a new color representation model is proposed to estimate the intrinsic color of each pixel according to the global color distribution of the image. The underlying assumption of our proposed model is that all colors in a natural image can be approximated by a limited number of chrominance values (dominant colors). Speci cally, the color statistics are counted by 2D histogram analysis. Then, we approximate the color distribution by the sum of a set of Gaussian mixture functions (GMF), whose centroids are the dominant colors (Dc) of the image. By choosing colors around each Dc, the possible intrinsic colors for each pixel can be comprehensively and e fficiently selected. Considering the fast development of IP-based video broadcasting, we present a data hiding scheme that can protect the chroma keying results when the image/video data is recorded in the JPEG/H.264 format. According to our simulation, the proposed chroma keying system generates high quality composited images that are little a ected by re ecting, background shading, and intrinsic color missing.

This thesis proposes a novel chroma keying method based on stereo images, which can be applied to post-process the alpha matte generated by any existing matting approach. Given a pair of stereo images, a new matting Laplacian matrix is constructed based on the affinities between matching pixels and their neighbors from two frames. Based on the new matting Laplacian matrix, a new cost function is also formulated to estimate alpha values of the reference image through the propagation between stereo images.

La tecnología está en constante innovación y definitivamente en esta era cada vez se ha vuelto una parte esencial de nuestra vida. Todas las industrias se han visto involucrada por los diversos avances tecnológicos; y uno de ellos es la industria del cine. Una industria creada a partir de los pequeños avances tecnológicos en su época, como el cinematógrafo hasta los últimos avances de nuestros días como lo son las imágenes generadas por computadora. Dentro de la industria del cine tenemos a una muy importante, Hollywood, que hoy en día es muy exitosa y nos ofrece una gran variedad de películas de gran éxito, entre las cuales destaca las de superhéroes. En específico, Marvel comics que con sus personajes ha logrado posicionarse en esta industria, teniendo más de 30 películas. Llevando el mundo de las páginas de historieta hacia la gran pantalla. Ello debido a sus fantásticos personajes con características humanas y también a la tecnología que ayuda a recrear estos mundos que Stan Lee y Jack Kirby crearon hace décadas. Dos industrias nacidas y desarrolladas en una época pasada vuelven a resurgir a través de estos avances tecnológicos para seguir entreteniendo y enseñando a los más jóvenes. En un sociedad plagada de acontecimientos peligrosos donde se necesita un héroe en quien confiar, una esperanza a la sociedad a su día a día. Vuelven los superhéroes del pasado con un nuevo rostro gracias a la nueva era tecnología que nos permite creer en que lo imposible es posible. / It is widely believed that nowadays technology has become a escencial part of our lives. One of the biggest impact of it's development had affected cinematography industry which has been increasing due to the new ways of technology. One of these industries is Hollywood, which as we all know offers a huge variety of successful movies and the most notorious is Marvel that has revolutionise all the comic worlds. Marvel has more than 30 movies most of them had used CGI and advance technology that helped to appreciate sophisticated graphics. The reason of this huge success is on the superheroes character's that has a lot of human characteristics and it seems to be more like us. In addition to this, the comics where this movies are based on are fantastic and creates to the spectator the feeling of been in somewhere else for a couple of hours. Finally, Marvel as an important industry has been dealing with all the technology development that is a big part of all their achievement. / Trabajo de investigación

Spiderwort (Tradescantia virginiana) is a flowering herbaceous perennial. Little information is available about its production requirements. This project’s purpose was to determine fertilizer and PGR rates for high quality growth of Spiderwort in a greenhouse production setting. The first experiment screened three plant growth regulators (PGRs) at ascending rates on three T. virginiana cultivars. The most effective rates for height suppression were paclobutrazol at 120 mgּL-1, uniconazole at 45 mgּL-1, and flurprimidol at 45 mgּL-1. The second experiment was divided into two parts. The first screened three T. virginiana cultivars for their growth response to several nitrogen (N) rates. The second experiment used results from the first experiment and examined two cultivars response to a basic fertilizer. For experiment 1, N rates between 100 and 200 mg‧L-1 resulted in quality plant growth. The second experiment showed little difference between height, width and flowering of both cultivars with these N rates. Plant quality was similar for plants fertilized with 100 and 200 mgּL-1 N at the end of both experiments. The third study examined how fertilization rate affects the persistence of PGR growth control. PGR rates identified as effective in experiment 1 were used. Plants fertilized with 200 mgּL-1 N were taller than those fertilized with 100 mgּL-1 N, regardless of PGR treatment. PGRs did not suppress plant growth; plant quality was similar regardless of treatment. The results of these studies indicate that PGR effectiveness in suppressing plant height may be dependent upon season, with PGR application necessary only during the spring growing season. / Master of Science

[pt] A indústria de cinema e TV tem usado amplamente a técnica de Chroma Key, também conhecida por Blue Screen Matting. Esta técnica revolucionou, ao longo do tempo, a indústria do entretenimento, permitindo que cenas impossíveis de serem criadas se tornassem realidade. A evolução dessa técnica permitiu que produções complexas passassem a ter melhor controle e custos mais baixos. Porém, essa técnica conta com uma série de etapas de preparação, que demandam recursos financeiros elevados e planejamento preciso. Ademais, erros de continuidade costumam criar sérios problemas na pós-produção. Atualmente, a indústria de entretenimento está procurando outras técnicas de matting que funcionem com fundos variados. O uso destas técnicas ainda está restrita a trabalhos acadêmicos e a softwares de manipulação de imagens estáticas. O presente trabalho tem como objetivos fazer uma análise dos processos atuais de chroma key e partir para a proposta de uma técnica de matting com fundos variados em imagens de alta definição (HD – High Definition). Dois métodos para o cálculo de valores de alpha são apresentados: um método global baseado em clusters e um método local baseado em potencial elétrico. / [en] The film and broadcast industry have been massively using the Chroma Key technique, also known as Blue Screen Matting. This technique deeply transformed the entertainment industry, allowing impossible scenes become reality. The evolution of this technique allowed that complex productions could have better control and lower costs. However, this technique needs a sequence of preparation stages, which require high budgets and precise planning. Furthermore, continuity errors usually cause serious post-production problems. Currently, the entertainment industry is searching for other matting techniques that work on any kind of background. The use of these techniques is still restricted to academic works and softwares of still image manipulation. The present work has the goal of making an analysis of the current chroma key processes and aims to propose a matting technique over any type of background in High Definition images. Two methods of calculating alpha values are presented: a local method based on clusters and a local one based on electric potential.

Alpha matting is one of the key techniques in image processing and is used to extract accurate foreground from a still image or video sequences. Chroma keying is a special case of alpha matting with a solid background color. Color spill is one of the difficulties in chroma keying, and it has not been effectively solved by current methods. Sometimes, an image contains both reflected regions and transparent regions. When the foreground in such images is chroma keyed, reflection on the foreground is often falsely treated as transparency and causes unreal foreground extraction and composition. This problem is called color spill. Color spill suppression aims to extract the opaque foreground with the correct transparency descriptor (i.e. alpha value) and remove the reflected background color on it. When the background color presented on the foreground is simultaneously caused by reflection and transparency, color spill suppression becomes extremely challenging. It is because that the reflection removal and the actual transparency estimation is a dilemma. Our proposed method for color spill suppression is to separate reflected regions from transparent regions, and process reflected regions as foreground while keeping transparency unchanged at the same time. In this thesis, we propose a novel method for color spill suppression for chroma keying. The quality of the estimated alpha matte could be significantly improved. In our approach, we suppress color spill by using the polarization and the optical flow algorithm based on disparity estimation. Specifically, we make the assumption that reflection changes more than transparency when the scene is captured by a binocular camera with a polaroid filter. Based on this assumption, we took stereo images with polarization filter, registered stereo images by optical flow and conducted the variance analysis on histograms of input images to separate transparency and reflection. Our experiments show that the opaque foreground with background color spill can be reliably extracted while the real transparency can be kept.

This thesis proposes a new chroma keying method that can automatically detect background, foreground, and unknown regions. For background color detection, we use K-means clustering in color space to calculate the limited number of clusters of background colors. We use spatial information to clean the background regions and minimize the unknown regions. Our method only needs minimum inputs from user. For unknown regions, we implement the alpha matte based on Wang's robust matting algorithm, which is considered one of the best algorithms in the literature, if not the best. Wang's algorithm is based on modified random walk. We proposed a better color selection method, which improves matting results in the experiments. In the thesis, a detailed implementation of robust matting is provided. The experimental results demonstrate that our proposed method can handle images with one background color, images with gridded background, and images with difficult regions such as complex hair stripes and semi-transparent clothes.

This thesis proposes a new chroma keying method that can automatically detect background, foreground, and unknown regions. For background color detection, we use K-means clustering in color space to calculate the limited number of clusters of background colors. We use spatial information to clean the background regions and minimize the unknown regions. Our method only needs minimum inputs from user. For unknown regions, we implement the alpha matte based on Wang's robust matting algorithm, which is considered one of the best algorithms in the literature, if not the best. Wang's algorithm is based on modified random walk. We proposed a better color selection method, which improves matting results in the experiments. In the thesis, a detailed implementation of robust matting is provided. The experimental results demonstrate that our proposed method can handle images with one background color, images with gridded background, and images with difficult regions such as complex hair stripes and semi-transparent clothes.

Photorealism is what visual effects are all about most of the time. This report entails digital compositing and studio lighting, in relation to Chroma key film material, aimed to give a photorealistic impression.    One of the identified problems in this report is that compositors may get Chroma key footage where the lighting is done poorly, which means a lot of extra work for the compositors and it might even make it impossible to create the desired end result.    Another problem recognized is that the knowledge that these professions possess is often tacit, not available in texts or even functionally defined.    Considering these problems, the purpose of this report is to articulate and try the tacit knowledge found in respect to these research questions: Which factors can alter the photorealistic impression of filmed Chroma key material? To what extent can different factors be altered in the compositing process, for a photorealistic result? How can a photorealistic result from composited Chroma key material be enabled and facilitated, with focus on studio lighting?       Methods used to answer these questions are interviews with compositors, a case study of a small video production, and the production of video clips, including studio lighting and compositing.    While professionals often write about the importance of consistency in image characteristics between different element that are composited together, this report defines which specific features that ought to be consistent, for a photorealistic result.    Further findings are focused on the limitations of the compositor; i.e. the features that are possible to manipulate and the features that have to be set correctly when filming in the studio, to enable a photorealistic outcome. Nonetheless, the main focus will be on the features of lighting set in the Chroma key film studio.    In fact, there are many features that are crucial for enabling and facilitating the compositing of a photorealistic end product. While some of the findings are new, others confirm what has already been presented.

This thesis proposes a new chroma keying method that can automatically detect background, foreground, and unknown regions. For background color detection, we use K-means clustering in color space to calculate the limited number of clusters of background colors. We use spatial information to clean the background regions and minimize the unknown regions. Our method only needs minimum inputs from user. For unknown regions, we implement the alpha matte based on Wang's robust matting algorithm, which is considered one of the best algorithms in the literature, if not the best. Wang's algorithm is based on modified random walk. We proposed a better color selection method, which improves matting results in the experiments. In the thesis, a detailed implementation of robust matting is provided. The experimental results demonstrate that our proposed method can handle images with one background color, images with gridded background, and images with difficult regions such as complex hair stripes and semi-transparent clothes.