O rastreamento de objetos em vídeos representa um importante problema na área de processamento de imagens, quer seja pelo grande número de aplicações envolvidas, ou pelo grau de complexidade que pode ser apresentado. Como exemplo de aplicações, podemos citar sua utilização em áreas como robótica móvel, interface homem-máquina, medicina, automação de processo industriais até aplicações mais tracionais como vigilância e monitoramento de trafego. O aumento na complexidade do rastreamento se deve principalmente a interação do objeto rastreado com outros elementos da cena do vídeo, especialmente nos casos de oclusões parciais ou totais. Quando uma oclusão ocorre a informação sobre a localização do objeto durante o rastreamento é perdida parcial ou totalmente. Métodos de filtragem estocástica, utilizados para o rastreamento de objetos, como os Filtros de Partículas não apresentam resultados satisfatórios na presença de oclusões totais, onde temos uma descontinuidade na trajetória do objeto. Portanto torna-se necessário o desenvolvimento de métodos específicos para tratar o problema de oclusão total. Nesse trabalho, nós desenvolvemos uma abordagem para tratar o problema de oclusão total no rastreamento de objetos utilizando Filtro de Partículas baseados em Monte Carlo via Cadeia de Markov (MCCM) com função geradora de partículas adaptativa. Durante o rastreamento do objeto, em situações onde não há oclusões, nós utilizamos uma função de probabilidade geradora simétrica. Entretanto, quando uma oclusão total, ou seja, uma descontinuidade na trajetória é detectada, a função geradora torna-se assimétrica, criando um termo de “inércia” ou “arraste” na direção do deslocamento do objeto. Ao sair da oclusão, o objeto é novamente encontrado e a função geradora volta a ser simétrica novamente. / The object tracking on video is an important task in image processing area either for the great number of involved applications, or for the degree of complexity that can be presented. How example of application, we can cite its use from robotic area, machine-man interface, medicine, automation of industry process to vigilance and traffic control applications. The increase of complexity of tracking is occasioned principally by interaction of tracking object with other objects on video, specially when total or partial occlusions occurs. When a occlusion occur the information about the localization of tracking object is lost partially or totally. Stochastic filtering methods, like Particle Filter do not have satisfactory results in the presence of total occlusions. Total occlusion can be understood like discontinuity in the object trajectory. Therefore is necessary to develop specific method to handle the total occlusion task. In this work, we develop an approach to handle the total occlusion task using MCMC-Particle Filter with adaptive sampling probability function. When there is not occlusions we use a symmetric probability function to sample the particles. However, when there is a total occlusion, a discontinuity in the trajectory is detected, and the probability sampling function becomes asymmetric. This break of symmetry creates a “drift” or “inertial” term in object shift direction. When the tracking object becomes visible (after the occlusion) it is found again and the sampling function come back to be symmetric.

O rastreamento de objetos em vídeos representa um importante problema na área de processamento de imagens, quer seja pelo grande número de aplicações envolvidas, ou pelo grau de complexidade que pode ser apresentado. Como exemplo de aplicações, podemos citar sua utilização em áreas como robótica móvel, interface homem-máquina, medicina, automação de processo industriais até aplicações mais tracionais como vigilância e monitoramento de trafego. O aumento na complexidade do rastreamento se deve principalmente a interação do objeto rastreado com outros elementos da cena do vídeo, especialmente nos casos de oclusões parciais ou totais. Quando uma oclusão ocorre a informação sobre a localização do objeto durante o rastreamento é perdida parcial ou totalmente. Métodos de filtragem estocástica, utilizados para o rastreamento de objetos, como os Filtros de Partículas não apresentam resultados satisfatórios na presença de oclusões totais, onde temos uma descontinuidade na trajetória do objeto. Portanto torna-se necessário o desenvolvimento de métodos específicos para tratar o problema de oclusão total. Nesse trabalho, nós desenvolvemos uma abordagem para tratar o problema de oclusão total no rastreamento de objetos utilizando Filtro de Partículas baseados em Monte Carlo via Cadeia de Markov (MCCM) com função geradora de partículas adaptativa. Durante o rastreamento do objeto, em situações onde não há oclusões, nós utilizamos uma função de probabilidade geradora simétrica. Entretanto, quando uma oclusão total, ou seja, uma descontinuidade na trajetória é detectada, a função geradora torna-se assimétrica, criando um termo de “inércia” ou “arraste” na direção do deslocamento do objeto. Ao sair da oclusão, o objeto é novamente encontrado e a função geradora volta a ser simétrica novamente. / The object tracking on video is an important task in image processing area either for the great number of involved applications, or for the degree of complexity that can be presented. How example of application, we can cite its use from robotic area, machine-man interface, medicine, automation of industry process to vigilance and traffic control applications. The increase of complexity of tracking is occasioned principally by interaction of tracking object with other objects on video, specially when total or partial occlusions occurs. When a occlusion occur the information about the localization of tracking object is lost partially or totally. Stochastic filtering methods, like Particle Filter do not have satisfactory results in the presence of total occlusions. Total occlusion can be understood like discontinuity in the object trajectory. Therefore is necessary to develop specific method to handle the total occlusion task. In this work, we develop an approach to handle the total occlusion task using MCMC-Particle Filter with adaptive sampling probability function. When there is not occlusions we use a symmetric probability function to sample the particles. However, when there is a total occlusion, a discontinuity in the trajectory is detected, and the probability sampling function becomes asymmetric. This break of symmetry creates a “drift” or “inertial” term in object shift direction. When the tracking object becomes visible (after the occlusion) it is found again and the sampling function come back to be symmetric.

The current method for displacement estimation for homodyne Michelson interferometer is biased and gives little information about the statistical properties of the estimate. This thesis suggests an alternative estimation method, which has the potential to address these shortcomings. The method is based on a bootstrap Particle smoother, and gives similar displacement estimate quality compared to the least squares based method that is commonly used today. It is however significantly more computationally intensive, and hence the estimation quality has to be improved, while reducing the execution time, to obtain an algorithm that improves on the current one. In total, four estimation methods, based on particle filters or particle smoothers, are implemented in Matlab and evaluated. The recommended method is the most accurate one and is simple to implement in other programming languages. Most of the evaluation is done based on simulated data, but the three methods that work are tested on measured data as well. They all give reasonable displacement estimates for the measured data, but as the true displacement is unknown, the quality of the estimates cannot be assessed based on the measured data. Apart from the evaluation of the estimation methods, an introduction to both particle filtering and interferometry is given in the report, as well as a summary of the current, least squares based, estimator.

O presente trabalho procura estimar um modelo DSGE para o Brasil no período após a adoção do sistema de metas de inflação no Brasil. A estimação é feita com um filtro de partículas, que é um método não-linear. O modelo utilizado é o de Cristiano et al. (2005) com a modificação na regra de política monetária, de modo a incorporar a utilizada em Amisano e Tristani (2010). Com isso, assume-se que a meta de inflação segue um passeio aleatório, o que faz com que o modelo não tenha estado estacionário. A meta estimada aponta que na crise de 2008 e 2009 houve um desvio da meta de inflação utilizada em relação à divulgada. Houve também um desvio da meta utilizada na troca de gestão da autoridade monetária em 2011, segundo as estimações realizadas. Os resultados sugerem que o compromisso com a convergência para o centro da meta de inflação estipulada não ocorre ao longo de todo o período de análise. / This study aims to estimate a DSGE model for Brazil after the adoption of the Brazilian inflation targeting system. We estimate using a particle filter, which is a non-linear method of estimation. We use the model developed in Cristiano et al. (2005), changing its monetary policy rule for the one used by Amisano and Tristani (2010). With this modification, we assume that the inflation target follows a random walk, what makes the model loses its steady-state. The estimated target deviates from the official target during the 2008/09 world recession. According to our estimation, there was also a deviation from the official inflation target in 2011, when the Brazilian central bank’s chairman changed from Henrique Meirelles to Alexandre Tombini. Our results point out that the commitment with the inflation convergence to the center of the inflation target does not occur during our analysis’ entire period.

abstract: Dynamic channel selection in cognitive radio consists of two main phases. The first phase is spectrum sensing, during which the channels that are occupied by the primary users are detected. The second phase is channel selection, during which the state of the channel to be used by the secondary user is estimated. The existing cognitive radio channel selection literature assumes perfect spectrum sensing. However, this assumption becomes problematic as the noise in the channels increases, resulting in high probability of false alarm and high probability of missed detection. This thesis proposes a solution to this problem by incorporating the estimated state of channel occupancy into a selection cost function. The problem of optimal single-channel selection in cognitive radio is considered. A unique approach to the channel selection problem is proposed which consists of first using a particle filter to estimate the state of channel occupancy and then using the estimated state with a cost function to select a single channel for transmission. The selection cost function provides a means of assessing the various combinations of unoccupied channels in terms of desirability. By minimizing the expected selection cost function over all possible channel occupancy combinations, the optimal hypothesis which identifies the optimal single channel is obtained. Several variations of the proposed cost-based channel selection approach are discussed and simulated in a variety of environments, ranging from low to high number of primary user channels, low to high levels of signal-to-noise ratios, and low to high levels of primary user traffic. / Dissertation/Thesis / M.S. Electrical Engineering 2014

O presente trabalho procura estimar um modelo DSGE para o Brasil no período após a adoção do sistema de metas de inflação no Brasil. A estimação é feita com um filtro de partículas, que é um método não-linear. O modelo utilizado é o de Cristiano et al. (2005) com a modificação na regra de política monetária, de modo a incorporar a utilizada em Amisano e Tristani (2010). Com isso, assume-se que a meta de inflação segue um passeio aleatório, o que faz com que o modelo não tenha estado estacionário. A meta estimada aponta que na crise de 2008 e 2009 houve um desvio da meta de inflação utilizada em relação à divulgada. Houve também um desvio da meta utilizada na troca de gestão da autoridade monetária em 2011, segundo as estimações realizadas. Os resultados sugerem que o compromisso com a convergência para o centro da meta de inflação estipulada não ocorre ao longo de todo o período de análise. / This study aims to estimate a DSGE model for Brazil after the adoption of the Brazilian inflation targeting system. We estimate using a particle filter, which is a non-linear method of estimation. We use the model developed in Cristiano et al. (2005), changing its monetary policy rule for the one used by Amisano and Tristani (2010). With this modification, we assume that the inflation target follows a random walk, what makes the model loses its steady-state. The estimated target deviates from the official target during the 2008/09 world recession. According to our estimation, there was also a deviation from the official inflation target in 2011, when the Brazilian central bank’s chairman changed from Henrique Meirelles to Alexandre Tombini. Our results point out that the commitment with the inflation convergence to the center of the inflation target does not occur during our analysis’ entire period.

Localização e Mapeamento Simultâneos (SLAM) é uma das tarefas mais difíceis em robótica móvel, uma vez que existe uma dependência mútua entre a estimativa da localização do robô e a construção do mapa de ambiente. As estratégias de SLAM mais bem sucedidas focam na construção de um mapa métrico probabilístico empregando técnicas de filtragem Bayesiana. Embora tais métodos permitam a construção de soluções localmente consistentes e coerentes, o SLAM continua sendo um problema crítico em operações em ambientes grandes. Para contornar esta limitação, muitas estratégias dividem o ambiente em pequenas regiões, e formulam o problema de SLAM como uma combinação de múltiplos submapas métricos precisos associados em um mapa topológico. Este trabalho propõe um método de SLAM baseado nos algoritmos DP-SLAM (Distributed Particle SLAM) e SegSlam (Segmented SLAM). SegSLAM é um algoritmo que cria múltiplos submapas para cada região do ambiente, e posteriormente constrói o mapa global selecionando combinações de submapas. Por sua vez, DP-SLAM é um algoritmo de filtro de particulas Rao-Blackwellized que utiliza uma representação distribuída eficiente dos mapas das partículas, juntamente com a árvore de ascendência das partículas. A característica distribuída destas estruturas é favorável para a combinação de diferentes segmentos de mapa localmente precisos, o que aumenta a diversidade de soluções. O algoritmo proposto nesta dissertação, chamado SDP-SLAM, segmenta e combina diferentes hipóteses de trajetórias do robô, a fim de reconstruir o mapa do ambiente. Nossas principais contribuições são o desenvolvimento de novas estratégias para o casamento de submapas e para a estimativa de boas combinações de submapas. O SDP-SLAM foi avaliado através de experimentos realizados por um robô móvel operando em ambientes reais e simulados. / Simultaneous Localization and Mapping (SLAM) is one of the most difficult tasks in mobile robotics, since there is a mutual dependency between the estimation of the robot pose and the construction of the environment map. Most successful strategies in SLAM focus in building a probabilistic metric map employing Bayesian filtering techniques. While these methods allow the construction of consistent and coherent local solutions, the SLAM remains a critical problem in operations within large environments. To circumvent this limitation, many strategies divide the environment in small regions, and formulate the SLAM problem as a combination of multiple precise metric submaps associated in a topological map. This work proposes a SLAM method based on the Distributed Particle SLAM (DPSLAM) and the Segmented SLAM (SegSLAM) algorithms. SegSLAM is an algorithm that generates multiple submaps for every region of the environment, and then build the global map by selecting combinations of submaps. DP-SLAM is a Rao-Blackwellized particle filter algorithm that uses an efficient distributed representation of the particles maps associated with an ancestry tree of the particles. The distributed characteristic of these structures favors the combination of locally accurate map segments, that can increase the diversity of global level solutions. The algorithm proposed in this dissertation, called SDP-SLAM, segments and combines different hypotheses of robot trajectories to reconstruct the environment map. Our main contributions are the development of novel strategies for the matching of submaps and for the estimation of good submaps combinations. SDP-SLAM was evaluated through experiments performed by a mobile robot operating in real and simulated environments.

Cette thèse s'intéresse à l'étude et au développement de méthodes de pistage mono et multicible en contexte Track-Before-Detect (TBD) par filtrage particulaire. Contrairement à l'approche classique qui effectue un seuillage préalable sur les données avant le pistage, l'approche TBD considère directement les données brutes afin de réaliser conjointement la détection et le pistage des différentes cibles. Il existe plusieurs solutions à ce problème, néanmoins cette thèse se restreint au cadre bayésien des Modèles de Markov Cachés pour lesquels le problème TBD peut être résolu à l'aide d'approximations particulaires. Dans un premier temps, nous nous intéressons à des méthodes particulaires monocibles existantes pour lesquels nous proposons différentes lois instrumentales permettant l'amélioration des performances en détection et estimation. Puis nous proposons une approche alternative du problème monocible fondée sur les temps d'apparition et de disparition de la cible; cette approche permet notamment un gain significatif au niveau du temps de calcul. Dans un second temps, nous nous intéressons au calcul de la vraisemblance en TBD -- nécessaire au bon fonctionnement des filtres particulaires -- rendu difficile par la présence des paramètres d'amplitudes des cibles qui sont inconnus et fluctuants au cours du temps. En particulier, nous étendons les travaux de Rutten et al. pour le calcul de la vraisemblance au modèle de fluctuations Swerling et au cas multicible. Enfin, nous traitons le problème multicible en contexte TBD. Nous montrons qu'en tenant compte de la structure particulière de la vraisemblance quand les cibles sont éloignées, il est possible de développer une solution multicible permettant d'utiliser, dans cette situation, un seule filtre par cible. Nous développons également un filtre TBD multicible complet permettant l'apparition et la disparition des cibles ainsi que les croisements. / This thesis deals with the study and the development of mono and multitarget tracking methods in a Track-Before-Detect (TBD) context with particle filters. Contrary to the classic approach that performs before the tracking stage a pre-detection and extraction step, the TBD approach directly works on raw data in order to jointly perform detection and tracking. Several solutions to this problem exist, however this thesis is restricted to the particular Hidden Markov Models considered in the Bayesian framework for which the TBD problem can be solved using particle filter approximations.Initially, we consider existing monotarget particle solutions and we propose several instrumental densities that allow to improve the performance both in detection and in estimation. Then, we propose an alternative approach of the monotarget TBD problem based on the target appearance and disappearance times. This new approach, in particular, allows to gain in terms of computational resources. Secondly, we investigate the calculation of the measurement likelihood in a TBD context -- necessary for the derivation of the particle filters -- that is difficult due to the presence of the target amplitude parameters that are unknown and fluctuate over time. In particular, we extend the work of Rutten et al. for the likelihood calculation to several Swerling models and to the multitarget case. Lastly, we consider the multitarget TBD problem. By taking advantage of the specific structure of the likelihood when targets are far apart from each other, we show that it is possible to develop a particle solution that considers only a particle filter per target. Moreover, we develop a whole multitarget TBD solution able to manage the target appearances and disappearances and also the crossing between targets.

Abstract The Earth’s magnetic field (MF) has been used for navigation for centuries. Man-made metallic structures, such as steel reinforcements in buildings, cause local distortions to the Earth’s magnetic field. Up until the recent decade, these distortions have been mostly considered as a source of error in indoor localization, as they interfere with the compass direction. However, as the distortions are temporally stable and spatially distinctive, they provide a unique magnetic landscape that can be used for constructing a map for indoor localization purposes, as noted by recent research in the field. Most approaches rely on manually collecting the magnetic field map, a process that can be both tedious and error-prone. In this thesis, the map is collected by a robotic platform with minimal sensor equipment. It is shown that a mere magnetometer along with odometric information suffices to construct the map via a simultaneous localization and mapping (SLAM) procedure that builds on the Rao-Blackwellized particle filter as means for recursive Bayesian estimation. Furthermore, the maps are shown to achieve decimeter level localization accuracy that combined with the extremely low-cost hardware requirements makes the presented methods very lucrative for domestic robots. In addition, general auxiliary methods for effective sampling and dealing with uncertainties are presented. Although the methods presented here are devised in mobile robotics context, most of them are also applicable to mobile device-based localization, for example, with little modifications. Magnetic field localization offers a promising alternative to WiFi-based methods for achieving GPS-level localization indoors. This is motivated by the rapidly growing indoor location market. / Tiivistelmä Maan magneettikenttään perustuvat kompassit ovat ohjanneet merenkäyntiä vuosisatojen ajan. Rakennusten metallirakenteet aiheuttavat paikallisia häiriöitä tähän magneettikenttään, minkä vuoksi kompasseja on pidetty epäluotettavina sisätiloissa. Vasta viimeisen vuosikymmenen aikana on huomattu, että koska nämä häiriöt ovat ajallisesti pysyviä ja paikallisesti hyvin erottelevia, niistä voidaan muodostaa jokaiselle rakennukselle yksilöllinen häiriöihin perustuva magneettinen kartta, jota voidaan käyttää sisätiloissa paikantamiseen. Suurin osa tämänhetkisistä magneettikarttojen sovelluksista perustuu kartan käsin keräämiseen, mikä on sekä työlästä että tarjoaa mahdollisuuden inhimillisiin virheisiin. Tämä väitöstutkimus tarttuu ongelmaan laittamalla robotin hoitamaan kartoitustyön ja näyttää, että robotti pystyy itsenäisesti keräämään magneettisen kartan hyödyntäen pelkästään magnetometriä ja renkaiden antamia matkalukemia. Ratkaisu perustuu faktoroituun partikkelisuodattimeen (RBPF), joka approksimoi täsmällistä rekursiivista bayesilaista ratkaisua. Robotin keräämien karttojen tarkkuus mahdollistaa paikannuksen n. 10 senttimetrin tarkkuudella. Vähäisten sensori- ja muiden vaatimusten takia menetelmä soveltuu erityisen hyvin koti- ja parvirobotiikkaan, joissa hinta on usein ratkaiseva tekijä. Tutkimuksessa esitellään lisäksi uusia apumenetelmiä tehokkaaseen näytteistykseen ja epävarmuuden hallintaan. Näiden käyttöala ei rajoitu pelkästään magneettipaikannukseen- ja kartoitukseen. Robotiikan sovellusten lisäksi tutkimusta motivoi voimakkaasti kasvava tarve älylaitteissa toimivalle sisätilapaikannukselle. Tämä avaa uusia mahdollisuuksia paikannukselle ympäristöissä, joissa GPS ei perinteisesti toimi.

In this thesis, robot navigation using the Particle Filter based FastSLAM approach for obstacle avoidance derived from a modified Velocity Potential Field method was investigated. A switching controller was developed to deal with robot’s efficient turning direction when close to obstacles. The determination of the efficient turning direction is based on the local map robot derived from its on board local sensing. The estimation of local map and robot path was implemented using the FastSLAM approach. A particle filter was utilized to obtain estimated robot path and obstacles (local map). When robot sensed only obstacles, the estimated robot positions was regarding to obstacles based the measurement of the distance between the robot and obstacles. When the robot detected the goal, estimation of robot path will switch to estimation with regard to the goal in order to obtain better estimated robot positions. Both simulation and experimental results illustrated that estimation with regard to the goal performs better than estimation regarding only to obstacles, because when robot travelled close to the goal, the residual error between estimated robot path and the ideal robot path becomes monotonously decreasing. When robot reached the goal, the estimated robot position and the ideal robot position converge. We investigated our proposed approach in two typical robot navigation scenarios. Simulations were accomplished using MATLAB, and experiments were conducted with the help of both MATLAB and LabVIEW. In simulations and experiments, the robot successfully chose efficiently turning direction to avoid obstacles and finally reached the goal.