Lane following Learning Based on Semantic Segmentation with Chroma Key and Image Superposition

There are various techniques to approach learning in autonomous driving; however, all of them suffer from some problems. In the case of imitation learning based on artificial neural networks, the system must learn to correctly identify the elements of the environment. In some cases, it takes a lot of effort to tag the images with the proper semantics. This is also relevant given the need to have very varied scenarios to train and to thus obtain an acceptable generalization capacity. In the present work, we propose a technique for automated semantic labeling. It is based on various learning phases using image superposition combining both scenarios with chromas and real indoor scenarios. This allows the generation of augmented datasets that facilitate the learning process. Further improvements by applying noise techniques are also studied. To carry out the validation, a small-scale car model is used that learns to automatically drive on a reduced circuit. A comparison with models that do not rely on semantic segmentation is also performed. The main contribution of our proposal is the possibility of generating datasets for real indoor scenarios with automatic semantic segmentation, without the need for endless human labeling tasks.

Illumination Space: A Feature Space for Radiance Maps

<p>From red sunsets to blue skies, the natural world contains breathtaking scenery with complex lighting which many computer graphics applications strive to emulate. Achieving such realism is a computationally challenging task and requires proficiency with rendering software. To aid in this process, radiance maps (RM) are a convenient storage structure for representing the real-world. In this form, it can be used to realistically illuminate synthetic objects or for backdrop replacement in chroma key compositing. An artist can also freely change a RM to another that better matches their desired lighting or background conditions. This motivates the need for a large collection of RMs such that an artist has a range of environmental conditions to choose from. Due to the practicality of RMs, databases of RMs have continually grown since its inception. However, a comprehensive collection of RMs is not useful without a method for searching through the collection. This thesis defines a semantic feature space that allows an artist to interactively browse through databases of RMs, with applications for both lighting and backdrop replacement in mind. The set of features are automatically extracted from the RMs in an offline pre-processing step, and are queried in real-time for browsing. Illumination features are defined to concisely describe lighting properties of a RM, allowing an artist to find a RM to illuminate their target scene. Texture features are used to describe visual elements of a RM, allowing an artist to search the database for reflective or backdrop properties for their target scene. A combination of the two sets of features allows an artist to search for RMs with desirable illumination effects which match the background environment.</p>

Illumination Space: A Feature Space for Radiance Maps

<p>From red sunsets to blue skies, the natural world contains breathtaking scenery with complex lighting which many computer graphics applications strive to emulate. Achieving such realism is a computationally challenging task and requires proficiency with rendering software. To aid in this process, radiance maps (RM) are a convenient storage structure for representing the real-world. In this form, it can be used to realistically illuminate synthetic objects or for backdrop replacement in chroma key compositing. An artist can also freely change a RM to another that better matches their desired lighting or background conditions. This motivates the need for a large collection of RMs such that an artist has a range of environmental conditions to choose from. Due to the practicality of RMs, databases of RMs have continually grown since its inception. However, a comprehensive collection of RMs is not useful without a method for searching through the collection. This thesis defines a semantic feature space that allows an artist to interactively browse through databases of RMs, with applications for both lighting and backdrop replacement in mind. The set of features are automatically extracted from the RMs in an offline pre-processing step, and are queried in real-time for browsing. Illumination features are defined to concisely describe lighting properties of a RM, allowing an artist to find a RM to illuminate their target scene. Texture features are used to describe visual elements of a RM, allowing an artist to search the database for reflective or backdrop properties for their target scene. A combination of the two sets of features allows an artist to search for RMs with desirable illumination effects which match the background environment.</p>

Chroma Key Enhance Students’ Verbal Participation During Form One English Language Lesson

Technology in the ESL classrooms is not something new.Using Chroma Key helps in making lesson more interactive, enjoyable and interesting.With the combination of physical and virtual technology, Chroma Keyorfrequently known as GreenScreen,creates a platformformeaningful learning. This study reveals how the use of Chroma Keyempowersa class of Form One, lower secondary school students to accomplish tasks and provides a comfortable environment to enhance students’ verbal participationsduring ESL lesson in Malaysia.

A LÍNGUA DE SINAIS EM MUSEUS: ACESSIBILIDADE ATRAVÉS DE GUIAS MULTIMÍDIAS

A promoção da acessibilidade para o surdo utilizando legendas em português nem sempre resolve a questão do acesso. Muitos surdos tem dificuldades de compreensão do português escrito e/ou falado, por isso mesmo, utilizam a língua de sinais como meio de comunicação e expressão. Uma medida financeiramente viável encontrada por alguns museus foi o de usar a tradução audiovisual acessível da língua de sinais. O objetivo deste artigo foi divulgar as estratégias de mediação para surdos que são utilizadas pelos centros de ciências e/ou museus bem como propor as diretrizes para a produção de vídeo guia acessível em língua de sinais a fim de auxiliar na elaboração de um material acessível de qualidade. Para isso, foi feito um levantamento bibliográfico, visitas a museus, entrevistas e análise de vídeos guias disponíveis em museus ao redor do mundo. Como resultado foram encontrados modelos de guias audiovisuais em museus do Rio de Janeiro, dos Estados Unidos e da Europa. Os modelos que utilizam a filmagem com chroma key são os mais apropriados, os vídeos devem ter legendas, as imagens são opcionais podendo ser inseridas ao lado do intérprete ou intercalando a imagem e o intérprete. Como estratégia de tradução deve se optar por realizar a datilologia das palavras/termos menos conhecidos seguido do sinal e/ou classificador especificador. Concluímos que esse modelo é financeiramente viável, em especial para centros de ciências e museus universitários que, por vezes, carecem de verba para a manutenção de suas exposições e atrações.

Painting By Numbers

Fractals have a property of self-similarity. They are similar to themselves in different regions, and similar to themselves on different length scales, so an enlargement of part of a fractal looks similar to the whole fractal. Benoit Mandelbrot pointed out that many objects, including coastlines, have a fractal structure. The mathematics of fractals dates back to Gaston Julia, who was seriously injured during the First World War and completed much of his work while recovering in hospital. Computer-generated imagery (CGI) is widely used in the video game and film industries. One technique for generating images of virtual scenes is known as ray-tracing. Filmed footage can be combined with computer-generated imagery using a technique known as chroma key. One of the most creative examples of computer art is the beautiful panoramic video in Pursuit of Venus by Lisa Reihana.