No description available.

Recovery of human pose from videos has become a highly active research area in the last decade because of many attractive potential applications, such as surveillance, non-intrusive motion analysis and natural human machine interaction. Video based full body pose estimation is a very challenging task, because of the high degree of articulation of the human body, the large variety of possible human motions, and the diversity of human appearances. Methods for tackling this problem can be roughly categorized as either discriminative or generative. Discriminative methods can work on single images, and are able to recover the human poses efficiently. However, the accuracy and generality largely depend on the training data. Generative approaches usually formulate the problem as a tracking problem and adopt an explicit human model. Although arbitrary motions can be tracked, such systems usually have difficulties in adapting to different subjects and in dealing with tracking failures. In this thesis, an accurate, efficient and robust human pose tracking system from a single view camera is developed, mainly following a generative approach. A novel discriminative feature is also proposed and integrated into the tracking framework to improve the tracking performance. The human pose tracking system is proposed within a particle filtering framework. A reconfigurable skeleton model is constructed based on the Acclaim Skeleton File convention. A basic particle filter is first implemented for upper body tracking, which fuses time efficient cues from monocular sequences and achieves real-time tracking for constrained motions. Next, a 3D surface model is added to the skeleton model, and a full body tracking system is developed for more general and complex motions, assuming a stereo camera input. Partitioned sampling is adopted to deal with the high dimensionality problem, and the system is capable of running in near real-time. Multiple visual cues are investigated and compared, including a newly developed explicit depth cue. Based on the comparative analysis of cues, which reveals the importance of depth and good bottom-up features, a novel algorithm for detecting and identifying endpoint body parts from depth images is proposed. Inspired by the shape context concept, this thesis proposes a novel Local Shape Context (LSC) descriptor specifically for describing the shape features of body parts in depth images. This descriptor describes the local shape of different body parts with respect to a given reference point on a human silhouette, and is shown to be effective at detecting and classifying endpoint body parts. A new type of interest point is defined based on the LSC descriptor, and a hierarchical interest point selection algorithm is designed to further conserve computational resources. The detected endpoint body parts are then classified according to learned models based on the LSC feature. The algorithm is tested using a public dataset and achieves good accuracy with a 100Hz processing speed on a standard PC. Finally, the LSC descriptor is improved to be more generalized. Both the endpoint body parts and the limbs are detected simultaneously. The generalized algorithm is integrated into the tracking framework, which provides a very strong cue and enables tracking failure recovery. The skeleton model is also simplified to further increase the system efficiency. To evaluate the system on arbitrary motions quantitatively, a new dataset is designed and collected using a synchronized Kinect sensor and a marker based motion capture system, including 22 different motions from 5 human subjects. The system is capable of tracking full body motions accurately using a simple skeleton-only model in near real-time on a laptop PC before optimization.

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.

This thesis is concerned with the development of techniques for analyzing the sequences of stereotypical electrical impulses within neurons known as spikes. Sequences of spikes, also called spike trains, transmit neural information; decoding them often provides details about the physiological processes generating the neural activity. Here, the statistical theory of event arrivals, called point processes, is applied to human muscle sympathetic spike trains, a peripheral nerve signal responsible for cardiovascular regulation. A novel technique that uses observed spike trains to dynamically derive information about the physiological processes generating them is also introduced. Despite the emerging usage of individual spikes in the analysis of human muscle sympathetic nerve activity, the majority of studies in this field remain focused on bursts of activity at or below cardiac rhythm frequencies. Point process theory applied to multi-neuron spike trains captured both fast and slow spiking rhythms. First, analysis of high-frequency spiking patterns within cardiac cycles was performed and, surprisingly, revealed fibers with no cardiac rhythmicity. Modeling spikes as a function of average firing rates showed that individual nerves contribute substantially to the differences in the sympathetic stressor response across experimental conditions. Subsequent investigation of low-frequency spiking identified two physiologically relevant frequency bands, and modeling spike trains as a function of hemodynamic variables uncovered complex associations between spiking activity and biophysical covariates at these two frequencies. For example, exercise-induced neural activation enhances the relationship of spikes to respiration but does not affect the extremely precise alignment of spikes to diastolic blood pressure. Additionally, a novel method of utilizing point process observations to estimate an internal state process with partially linear dynamics was introduced. Separation of the linear components of the process model and reduction of the sampled space dimensionality improved the computational efficiency of the estimator. The method was tested on an established biophysical model by concurrently computing the dynamic electrical currents of a simulated neuron and estimating its conductance properties. Computational load reduction, improved accuracy, and applicability outside neuroscience establish the new technique as a valuable tool for decoding large dynamical systems with linear substructure and point process observations.

abstract: In this thesis, an integrated waveform-agile multi-modal tracking-beforedetect sensing system is investigated and the performance is evaluated using an experimental platform. The sensing system of adapting asymmetric multi-modal sensing operation platforms using radio frequency (RF) radar and electro-optical (EO) sensors allows for integration of complementary information from different sensors. However, there are many challenges to overcome, including tracking low signal-to-noise ratio (SNR) targets, waveform configurations that can optimize tracking performance and statistically dependent measurements. Address some of these challenges, a particle filter (PF) based recursive waveformagile track-before-detect (TBD) algorithm is developed to avoid information loss caused by conventional detection under low SNR environments. Furthermore, a waveform-agile selection technique is integrated into the PF-TBD to allow for adaptive waveform configurations. The embedded exponential family (EEF) approach is used to approximate distributions of parameters of dependent RF and EO measurements and to further improve target detection rate and tracking performance. The performance of the integrated algorithm is evaluated using real data from three experimental scenarios. / Dissertation/Thesis / M.S. Electrical Engineering 2012

abstract: Buildings (approximately half commercial and half residential) consume over 70% of the electricity among all the consumption units in the United States. Buildings are also responsible for approximately 40% of CO2 emissions, which is more than any other industry sectors. As a result, the initiative smart building which aims to not only manage electrical consumption in an efficient way but also reduce the damaging effect of greenhouse gases on the environment has been launched. Another important technology being promoted by government agencies is the smart grid which manages energy usage across a wide range of buildings in an effort to reduce cost and increase reliability and transparency. As a great amount of efforts have been devoted to these two initiatives by either exploring the smart grid designs or developing technologies for smart buildings, the research studying how the smart buildings and smart grid coordinate thus more efficiently use the energy is currently lacking. In this dissertation, a "system-of-system" approach is employed to develop an integrated building model which consists a number of buildings (building cluster) interacting with smart grid. The buildings can function as both energy consumption unit as well as energy generation/storage unit. Memetic Algorithm (MA) and Particle Swarm Optimization (PSO) based decision framework are developed for building operation decisions. In addition, Particle Filter (PF) is explored as a mean for fusing online sensor and meter data so adaptive decision could be made in responding to dynamic environment. The dissertation is divided into three inter-connected research components. First, an integrated building energy model including building consumption, storage, generation sub-systems for the building cluster is developed. Then a bi-level Memetic Algorithm (MA) based decentralized decision framework is developed to identify the Pareto optimal operation strategies for the building cluster. The Pareto solutions not only enable multiple dimensional tradeoff analysis, but also provide valuable insight for determining pricing mechanisms and power grid capacity. Secondly, a multi-objective PSO based decision framework is developed to reduce the computational effort of the MA based decision framework without scarifying accuracy. With the improved performance, the decision time scale could be refined to make it capable for hourly operation decisions. Finally, by integrating the multi-objective PSO based decision framework with PF, an adaptive framework is developed for adaptive operation decisions for smart building cluster. The adaptive framework not only enables me to develop a high fidelity decision model but also enables the building cluster to respond to the dynamics and uncertainties inherent in the system. / Dissertation/Thesis / Ph.D. Industrial Engineering 2012

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.

This work presents a design of an indoor/outdoor SLAM technique combined with navigation for mobile robots. The system does not use any external beacons and relies on only one 2D range finder. This work focuses mainly on an implementation of already established algorithms which were significantly improved (which in effect helped also to overcome the set sensory limitations). To localize the robot and create a map of an unknown environment, we are using a variant of a Rao-Blackwell's particle filter. We also present techniques for navigating in the map and recognizing terrain types. The method for recognizing terrain types creates a much more unique map and also improves the outdoor localization. The outdoor environment that we focused on are city parks where the robot has to stay on designated paths.

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.

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.