All multimedia devices now incorporate video CODECs that comply with international video coding standards such as H.264 / MPEG4-AVC and the new High Efficiency Video Coding Standard (HEVC) otherwise known as H.265. Although the standard CODECs have been designed to include algorithms with optimal efficiency, large number of coding parameters can be used to fine tune their operation, within known constraints of for e.g., available computational power, bandwidth, consumer QoS requirements, etc. With large number of such parameters involved, determining which parameters will play a significant role in providing optimal quality of service within given constraints is a further challenge that needs to be met. Further how to select the values of the significant parameters so that the CODEC performs optimally under the given constraints is a further important question to be answered. This thesis proposes a framework that uses machine learning algorithms to model the performance of a video CODEC based on the significant coding parameters. Means of modelling both the Encoder and Decoder performance is proposed. We define objective functions that can be used to model the performance related properties of a CODEC, i.e., video quality, bit-rate and CPU time. We show that these objective functions can be practically utilised in video Encoder/Decoder designs, in particular in their performance optimisation within given operational and practical constraints. A Multi-objective Optimisation framework based on Genetic Algorithms is thus proposed to optimise the performance of a video codec. The framework is designed to jointly minimize the CPU Time, Bit-rate and to maximize the quality of the compressed video stream. The thesis presents the use of this framework in the performance modelling and multi-objective optimisation of the most widely used video coding standard in practice at present, H.264 and the latest video coding standard, H.265/HEVC. When a communication network is used to transmit video, performance related parameters of the communication channel will impact the end-to-end performance of the video CODEC. Network delays and packet loss will impact the quality of the video that is received at the decoder via the communication channel, i.e., even if a video CODEC is optimally configured network conditions will make the experience sub-optimal. Given the above the thesis proposes a design, integration and testing of a novel approach to simulating a wired network and the use of UDP protocol for the transmission of video data. This network is subsequently used to simulate the impact of packet loss and network delays on optimally coded video based on the framework previously proposed for the modelling and optimisation of video CODECs. The quality of received video under different levels of packet loss and network delay is simulated, concluding the impact on transmitted video based on their content and features.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2015-07-03T17:52:39Z No. of bitstreams: 1 Iris Corrêa das Chagas Linck.pdf: 1456080 bytes, checksum: ea4a6f659a229e845649c58baaf8cb23 (MD5) / Made available in DSpace on 2015-07-03T17:52:39Z (GMT). No. of bitstreams: 1 Iris Corrêa das Chagas Linck.pdf: 1456080 bytes, checksum: ea4a6f659a229e845649c58baaf8cb23 (MD5) Previous issue date: 2012 / FINEP - Financiadora de Estudos e Projetos / Neste trabalho é desenvolvido um algoritmo híbrido que simula o comportamento do Codificador/Decodificador de vídeo H.264/AVC, ou simplesmente CODEC H.264, utilizado no Sistema Brasileiro de Televisão Digital. O algoritmo proposto tem a finalidade de buscar a melhor configuração possível de seis dos principais parâmetros utilizados para a configuração do CODEC H.264. Este problema é abordado como um problema de otimização combinatória conhecido como Problema de Seleção de Partes e que é classificado como NP-Difícil. O algoritmo híbrido proposto, denominado Simulador de Metaheurísticas aplicado a um CODEC (SMC), foi desenvolvido com base em duas metaheurísticas: Busca Tabu e Algoritmo Genético. Os seis parâmetros de configuração a serem otimizados pelo SMC são: o bit rate; o frame rate; os parâmetros de quantização de quadros tipo B, tipo P e tipo I e a quantidade de quadros tipo B em um grupo de imagens (GOP – Group of Pictures). Os dois primeiros parâmetros mencionados atuam basicamente sobre a qualidade da imagem do vídeo enquanto que os demais parâmetros atuam diretamente na compressão do vídeo. Experimentos e testes foram feitos utilizandose o CODEC H.264 desenvolvido no Projeto Plataforma de Convergência Digital IPTV/TV Digital (DigConv). Nos experimentos o CODEC tem seus parâmetros configurados de acordo com os resultados obtidos pelo SMC. Um vídeo é codificado no CODEC H.264 para que se possa analisar a sua qualidade de imagem e o seu grau de compressão após o processo de codificação. É feita uma correlação entre esses resultados e a Função Objetivo do SMC. A qualidade da imagem é medida através da métrica mais utilizada na literatura, o PSNR (Peak Signal to Noise Ratio), que é calculada pelo próprio CODEC ao final da codificação de um vídeo. Verificouse que à medida que a Função Objetivo aumenta, o CODEC H.264 consegue obter uma melhor qualidade de imagem e um maior grau de compressão de vídeo. / In this work is developed a hybrid algorithm that simulates the behavior of the H.264/AVC video encoder/decoder, or simply H.264 video CODEC, used in the Brazilian System of Digital Television. The proposed algorithm intends to seek the best possible configuration of the six main parameters used for configuring the H.264 video CODEC. This problem is treated as a combinatorial optimization problem known as the Parties Selection Problem, which is classified as NP-Hard. The proposed hybrid algorithm, called Simulator Metaheuristcs applied to a CODEC (SMC), was developed based on two metaheuristics: Tabu Search and Genetic Algorithm. The six configuration parameters to be optimized by the SMC are the bit rate, frame rate, the parameters of quantization tables of type B, type I and type P and the amount of frames type B in a group of pictures (GOP - Group of Pictures).The first two parameters mentioned, work primarily on the quality of the video image while the other parameters act directly on the video compression. Experiments and tests were done using the video CODEC H.264 developed in Digital Convergence Platform IPTV/Digital TV Project (DigConv). DigConv Project. In the experiments the CODEC has its parameters set according to the results obtained by the SMC. Then, a video is encoded by the CODEC in order to analyze the video image quality and the video compression degree reached after the encoding process. It is made a correlation between these results and the objective function of the SMC. The picture quality is measured by the metric most often used in literature, the PSNR (Peak Signal to Noise Ratio), which is calculated by the CODEC at the end of a video encoding process. It was found that as the objective function has increased, the CODEC reached a better image quality and a higher video compression.