Conventional stereo vision systems rely on two spatially fixed cameras to gather depth information about a scene. The cameras typically have a fixed distance between them, known as the baseline. As the baseline increases, the estimated 3D information becomes more accurate, which makes it advantageous to have as large a baseline as possible. However, large baselines have problems whenever objects approach the cameras. The objects begin to leave the field of view of the cameras, making it impossible to determine where they are located in 3D space. This becomes especially important if an object of interest must be actuated upon and is approached by a vehicle. In an attempt to overcome this limitation, this thesis introduces a variable baseline stereo system that can adjust its baseline automatically based on the location of an object of interest. This allows accurate depth information to be gathered when an object is both near and far. The system was designed to operate under, and automatically move to a large range of different baselines. This thesis presents the mechanical design of the stereo boom. This is followed by a derivation of a control scheme that adjusts the baseline based on an estimate object location, which is gathered from stereo vision. This algorithm ensures that a certain incident angle on an object of interest is never surpassed. This maximum angle is determined by where a stereo correspondence algorithm, Semi-Global Block Matching, fails to create full reconstructions. / Master of Science

[pt] Este trabalho apresenta uma solução para o problema de posicionamento automático preciso de um corpo em um plano horizontal, atendendo à restrição de não gerar campo magnético significativo junto ao objeto a ser posicionado. A motivação do trabalho reside na necessidade, por parte do Laboratório de Supercondutividade Aplicada e Magnetismo (LSAM) do Departamento de Física, de um posicionador para experimentação em magnetocardiografia. Inicialmente são discutidas as tecnologias de automação aplicáveis ao problema, justificando-se a opção por um sistema pneumático de atuação. O sistema posicionar montado é então descrito em profundidade, abordando-se os aspectos relacionados à geometria do problema em questão, materiais, montagens mecânicas e o sistema de controle digital. A seguir é apresentada uma abordagem matemática para o problema de controle de posição em malha fechada, visando à definição de uma lei de controle aplicável ao caso em estudo. Alguns resultados analíticos são obtidos para controle de sistema caracterizados por atrito Coulombiano, ao mesmo tempo em que se desenvolve um modelo para simulação numérica da dinâmica de movimento do posicionador. Com base nestas duas ferramentas, é apresentada uma discussão sobre a aplicabilidade dos controladores da família PID ao caso específico considerado. Por fim, resultados reais obtidos com a lei de controle proposta são comparadores aos resultados simulados, mostrando-se a validade e a utilidade do modelo teórico. / [en] This thesis presents a solution or the problem of automatic precise positioning of na object in the horizontal plane, not generating any significative magnetic field in the region close to the object to be positioned. The study presented was developed as part of an effort to fulfill a necessity for a positioning system for magnetocardiography experimentation in the Magnetism and Applied Supercondutivity Laboratory of the Departament of Physics of this University. A discussion over applicable automation option is presents, along with a justification for a choice of a pneumatic actuating system. The whole precise positioning assembly is described in detail, including subjects such as movement geometry, material, mechanical structures and the digital control system. A mathematical study of the closed of the closed loop position control problem is then developed, aiming to define a control algorithm applicable to the problem. Algebraic analysis is used to describe the influence of Coulomb friction over the equations of motion of a proportional position control system, while a model for simulations experiments of the assembly´s positioning dynamics is developed. These tools are used as the basis for a discussion over the applicability of the PID controlers in the case in study. Moreover, the behavior of the proposed algorithm is recorded and compared to the results of the simulations, showing the correctness and the utility of the theoretical analysis.

Position of the vehicle is essential to navigate the vehicle along a desired path without any human interference. Global Positioning System (GPS) loses significant power due to signal attenuation caused by construction buildings. A good positioning system should have both good positioning accuracy and reliability. The purpose of this thesis is to implement a new positioning system using camera and examine the accuracy of the estimated vehicle position on a real-time scenario. The major focus of the thesis is to develop two algorithms for estimation of the position of the vehicle using a static camera and to evaluate the performance of the proposed algorithms. The proposed positioning system is based on two different processes. First process uses center of mass to estimate the position, while the second one utilizes gradient information to estimate the position of the vehicle. Two versions of the positioning systems are implemented. One version uses center of mass concept and background subtraction to estimate the position of the vehicle and the other version calculates gradients to estimate the position of the vehicle. Both algorithms are sensitive to point of view of the image i.e height of the camera. On comparing both algorithms, gradient based algorithm is less sensitive to the camera view. Finally, the performance is greater dependent on the height of the camera position for center of mass positioning system, as compared to the gradient positioning system but the accuracy of the systems can be improved by increasing the height of the camera. In terms of the speed of processing, the gradient positioning system is faster than the center of mass positioning system. The first algorithm, based on center of mass has 89.75\% accuracy with a standard deviation of 3 pixels and the second algorithm has an accuracy of 92.26\%. Accuracy of the system is estimated from the number of false detected positions.

This thesis solves design of functional device that will be able to automatically positioning back view mirrors according to the positio of driver face. Measuring position of the face provides stereovision of two webacams. The device is based on a computer Raspberry Pi 2 with designed expansion board. The created prototype can follow set view int the mirror with accuracy up to 7 cm (horizontally up to 5cm) in level of rear corner of a car. The results of this project validate design of automatic positioning mirror and it can be basis for specific implementations of the device in car.