<p><em>The first objective of this research has always been carry out a study of visual techniques SLAM (Simultaneous localization and mapping), specifically the type monovisual, less studied than the stereo. These techniques have been well studied in the world of robotics. These techniques are focused on reconstruct a map of the robot enviroment while maintaining its position information in that map. We chose to investigate a method to encode the points by the inverse of its depth, from the first time that the feature was observed. This method permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF).At first, the study mentioned it should be consolidated developing an application that implements this method. After suffering various difficulties, it was decided to make use of a platform developed by the same author of Slam method mentioned in MATLAB. Until then it had developed the tasks of calibration, feature extraction and matching. From that point, that application was adapted to the characteristics of our camera and our video to work. We recorded a video with our camera following a known trajectory to check the calculated path shown in the application. Corroborating works and studying the limitations and advantages of this method.</em></p>

<p>The first objective of this research has always been carry out a study of visual techniques SLAM (Simultaneous localization and mapping), specifically the type monovisual, less studied than the stereo. These techniques have been well studied in the world of robotics. These techniques are focused on reconstruct a map of the robot enviroment while maintaining its position information in that map. We chose to investigate a method to encode the points by the inverse of its depth, from the first time that the feature was observed. This method permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF).At first, the study mentioned it should be consolidated developing an application that implements this method. After suffering various difficulties, it was decided to make use of a platform developed by the same author of Slam method mentioned in MATLAB. Until then it had developed the tasks of calibration, feature extraction and matching. From that point, that application was adapted to the characteristics of our camera and our video to work. We recorded a video with our camera following a known trajectory to check the calculated path shown in the application. Corroborating works and studying the limitations and advantages of this method.</p>

The first objective of this research has always been carry out a study of visual techniques SLAM (Simultaneous localization and mapping), specifically the type monovisual, less studied than the stereo. These techniques have been well studied in the world of robotics. These techniques are focused on reconstruct a map of the robot enviroment while maintaining its position information in that map. We chose to investigate a method to encode the points by the inverse of its depth, from the first time that the feature was observed. This method permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF).At first, the study mentioned it should be consolidated developing an application that implements this method. After suffering various difficulties, it was decided to make use of a platform developed by the same author of Slam method mentioned in MATLAB. Until then it had developed the tasks of calibration, feature extraction and matching. From that point, that application was adapted to the characteristics of our camera and our video to work. We recorded a video with our camera following a known trajectory to check the calculated path shown in the application. Corroborating works and studying the limitations and advantages of this method.

The first objective of this research has always been carry out a study of visual techniques SLAM (Simultaneous localization and mapping), specifically the type monovisual, less studied than the stereo. These techniques have been well studied in the world of robotics. These techniques are focused on reconstruct a map of the robot enviroment while maintaining its position information in that map. We chose to investigate a method to encode the points by the inverse of its depth, from the first time that the feature was observed. This method permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF).At first, the study mentioned it should be consolidated developing an application that implements this method. After suffering various difficulties, it was decided to make use of a platform developed by the same author of Slam method mentioned in MATLAB. Until then it had developed the tasks of calibration, feature extraction and matching. From that point, that application was adapted to the characteristics of our camera and our video to work. We recorded a video with our camera following a known trajectory to check the calculated path shown in the application. Corroborating works and studying the limitations and advantages of this method.

"The use of cameras and computer vision algorithms to provide state estimation for robotic systems has become increasingly popular, particularly for small mobile robots and unmanned aerial vehicles (UAVs). These algorithms extract information from the camera images and perform simultaneous localization and mapping (SLAM) to provide state estimation for path planning, obstacle avoidance, or 3D reconstruction of the environment. High resolution cameras have become inexpensive and are a lightweight and smaller alternative to laser scanners. UAVs often have monocular camera or stereo camera setups since payload and size impose the greatest restrictions on their flight time and maneuverability. This thesis explores ORB-SLAM, a popular Visual SLAM method that is appropriate for UAVs. Visual SLAM is computationally expensive and normally offloaded to computers in research environments. However, large UAVs with greater payload capacity may carry the necessary hardware for performing the algorithms. The inclusion of general-purpose GPUs on many of the newer single board computers allows for the potential of GPU-accelerated computation within a small board profile. For this reason, an NVidia Jetson board containing an NVidia Pascal GPU was used. CUDA, NVidia’s parallel computing platform, was used to accelerate monocular ORB-SLAM, achieving onboard Visual SLAM on a small UAV. Committee members:"

Extrair informação de profundidade a partir de imagens bidimensionais é um importante problema na área de visão computacional. Diversas aplicações se beneficiam desta classe de algoritmos tais como: robótica, a indústria de entretenimento, aplicações médicas para diagnóstico e confecção de próteses e até mesmo exploração interplanetária. Esta aplicação pode ser dividida em duas etapas interdependentes: a estimação da posição e orientação da câmera no momento em que a imagem foi gerada, e a estimativa da estrutura tridimensional da cena. Este trabalho foca em técnicas de visão computacional usadas para estimar a trajetória de um veículo equipado com uma câmera, problema conhecido como odometria visual. Para obter medidas objetivas de eficiência e precisão, e poder comparar os resultados obtidos com o estado da arte, uma base de dados de alta precisão, bastante utilizada pela comunidade científica foi utilizada. No curso deste trabalho novas técnicas para rastreamento de detalhes, estimativa de posição de câmera, cálculo de posição 3D de pontos e recuperação de escala são propostos. Os resultados alcançados superam os mais bem ranqueados trabalhos na base de dados escolhida até o momento da publicação desta tese. / Recovering three-dimensional information from bi-dimensional images is an important problem in computer vision that finds several applications in our society. Robotics, entertainment industry, medical diagnose and prosthesis, and even interplanetary exploration benefit from vision based 3D estimation. The problem can be divided in two interdependent operations: estimating the camera position and orientation when each image was produced, and estimating the 3D scene structure. This work focuses on computer vision techniques, used to estimate the trajectory of a vehicle equipped camera, a problem known as visual odometry. In order to provide an objective measure of estimation efficiency and to compare the achieved results to the state-of-the-art works in visual odometry a high precision popular dataset was selected and used. In the course of this work new techniques for image feature tracking, camera pose estimation, point 3D position calculation and scale recovery are proposed. The achieved results outperform the best ranked results in the popular chosen dataset.

Methodologies are proposed for combining carrier-phase differential GPS (CDGPS), visual simultaneous localization and mapping (SLAM), and inertial measurements to obtain precise and globally-referenced position and attitude estimates of a rigid structure connecting a GPS receiver, a camera, and an inertial measurement unit (IMU). As part of developing these methodologies, observability of globally-referenced attitude based solely on GPS-based position estimates and visual feature measurements is proven. Determination of attitude in this manner eliminates the need for attitude estimates based on magnetometer and accelerometer measurements, which are notoriously susceptible to magnetic disturbances. This combination of navigation techniques, if coupled properly, is capable of attaining centimeter-level or better absolute positioning and degree-level or better absolute attitude accuracies in any space, both indoors and out. Such a navigation system is ideally suited for application to augmented reality (AR), which often employs a GPS receiver, a camera, and an IMU, and would result in tight registration of virtual elements to the real world. A prototype AR system is presented that represents a first step towards coupling CDGPS, visual SLAM, and inertial navigation. While this prototype AR system does not couple CDGPS and visual SLAM tightly enough to obtain some of the benefit of the proposed methodologies, the system is capable of demonstrating an upper bound on the precision that such a combination of navigation techniques could attain. Test results for the prototype AR system are presented for a dynamic scenario that demonstrate sub-centimeter-level positioning precision and sub-degree-level attitude precision. This level of precision would enable convincing augmented visuals. / text

No description available.

Orientador: Suely Cunha Amaro Mantovani / Resumo: A criação de robôs que podem operar autonomamente em ambientes controlados e não controlados tem sido, um dos principais objetivos da robótica móvel. Para que um robô possa navegar em um ambiente interno desconhecido, ele deve se localizar e ao mesmo tempo construir um mapa do ambiente que o rodeia, a este problema dá-se o nome de Localização e Mapeamento Simultâneos- SLAM. Tem-se como proposta neste trabalho para solucionar o problema do SLAM, o uso de um sensor RGB-D, com 6 graus de liberdade para perceber o ambiente, o qual é embarcado em um robô. O problema do SLAM pode ser solucionado estimando a pose - posição e orientação, e a trajetória do sensor no ambiente, de forma precisa, justificando a construção de um mapa em três dimensões (3D). Esta estimação envolve a captura consecutiva de frames do ambiente fornecidos pelo sensor RGB-D, onde são determinados os pontos mais acentuados das imagens através do uso de características visuais dadas pelo algoritmo ORB. Em seguida, a comparação entre frames consecutivos e o cálculo das transformações geométricas são realizadas, mediante o algoritmo de eliminação de correspondências atípicas, bPROSAC. Por fim, uma correção de inconsistências é efetuada para a reconstrução do mapa 3D e a estimação mais precisa da trajetória do robô, utilizando técnicas de otimização não lineares. Experimentos são realizados para mostrar a construção do mapa e o desempenho da proposta. / Doutor

Extrair informação de profundidade a partir de imagens bidimensionais é um importante problema na área de visão computacional. Diversas aplicações se beneficiam desta classe de algoritmos tais como: robótica, a indústria de entretenimento, aplicações médicas para diagnóstico e confecção de próteses e até mesmo exploração interplanetária. Esta aplicação pode ser dividida em duas etapas interdependentes: a estimação da posição e orientação da câmera no momento em que a imagem foi gerada, e a estimativa da estrutura tridimensional da cena. Este trabalho foca em técnicas de visão computacional usadas para estimar a trajetória de um veículo equipado com uma câmera, problema conhecido como odometria visual. Para obter medidas objetivas de eficiência e precisão, e poder comparar os resultados obtidos com o estado da arte, uma base de dados de alta precisão, bastante utilizada pela comunidade científica foi utilizada. No curso deste trabalho novas técnicas para rastreamento de detalhes, estimativa de posição de câmera, cálculo de posição 3D de pontos e recuperação de escala são propostos. Os resultados alcançados superam os mais bem ranqueados trabalhos na base de dados escolhida até o momento da publicação desta tese. / Recovering three-dimensional information from bi-dimensional images is an important problem in computer vision that finds several applications in our society. Robotics, entertainment industry, medical diagnose and prosthesis, and even interplanetary exploration benefit from vision based 3D estimation. The problem can be divided in two interdependent operations: estimating the camera position and orientation when each image was produced, and estimating the 3D scene structure. This work focuses on computer vision techniques, used to estimate the trajectory of a vehicle equipped camera, a problem known as visual odometry. In order to provide an objective measure of estimation efficiency and to compare the achieved results to the state-of-the-art works in visual odometry a high precision popular dataset was selected and used. In the course of this work new techniques for image feature tracking, camera pose estimation, point 3D position calculation and scale recovery are proposed. The achieved results outperform the best ranked results in the popular chosen dataset.