This thesis is concerned with the extraction of dense three-dimensional depth maps from sequences of two-dimensional greyscale images using correlation based matching. In particular the thesis is focused on the noise processes that occur in the depth map and the removal of that noise using nonlinear filters based on fuzzy systems. The depth from stereo algorithm is reviewed and a widely used correlation based matcher, the Sum Squared Difference (SSD) matcher, is introduced together with an established method of measuring sub-pixel disparities in stereo pairs of images. The noise in the disparity map associated with this matcher is investigated. The conjecture is made that a fuzzy inferencing system can be trained to perform a nonlinear filtering process which is more effective than conventional filters at removing the mixed impulsive and Gaussian-like noise present in the depth map. Six methods of training fuzzy systems of the Sugeno type based on the simulated annealing algorithm are proposed and tested by training fuzzy systems to approximate a simple function of two variables The thesis reviews existing fuzzy logic based filters and proposes a taxonomy for such systems. This distinguishes between direct and indirect acting fuzzy filters. An indirect acting fuzzy filter is applied to the task of smoothing a disparity map. The first order Sugeno fuzzy system is then proposed as an architecture that would be suitable as the basis for a direct acting fuzzy filter. This architecture is then applied to the task of smoothing depth maps derived from real and simulated data. The main contributions of the thesis are the identification of the Sugeno fuzzy system as a form of filter, the proposed training techniques, and the application of fuzzy filters to depth map smoothing.

M.Ing. / The induction machine is being widely implemented in motor control systems. Frequently not all the parameters of a system, which consists of an induction machine, an inverter, a load and a controller, are known. As the response of an induction machine is very sensitive to changes in these parameters, it is important to be able to design a control system that is independent of any parameter changes. In the past years, many control techniques have been developed for speed control of machine drives. The use of intelligent controllers has also recently been proposed to improve the response of the induction machine drive. With a fuzzy controller, we will try to eliminate as much as possible the effects of parameter variations that influence the response of the drive system. Since the fuzzy controller design is independent of the dynamic drive system model, the performance of the fuzzy controller is insensitive to any parameter changes. The fuzzy controller replaces the proportional- and integral controller (PI-controller) to determine the slip in a slip controller. The system for which the fuzzy controller is being investigated for implementation, is a battery operated wheelchair using two three phase cage rotor induction machines. These small; low voltage machines show strong parameter variations, making conventional control difficult. The fuzzy logic controller was investigated and the response compared with that of the PI-controller. The results indicated that at high rotor speeds the response of the fuzzy control strategy was favourable, but at low speeds ineffective. By modifying the fuzzy control strategy the rotor speed response can be optimised over the total speed zone.

A multi-input multi-output system to implement on-line process monitoring and intelligent control of complex curvature friction stir welding was proposed. An extra rotation axis was added to the existing three translation axes to perform friction stir welding of complex curvature other than straight welding line. A clamping system was designed for locating and holding the workpieces to bear the large force involved in the process between the welding tool and workpieces. Process parameters (feed rate, spindle speed, tilt angle and plunge depth), and process conditions (parent material and curvature), were used as factors for the orthogonal array experiments to collect sensor data of force, torque and tool temperature using multiple sensors and telemetry system. Using statistic analysis of the experimental data, sensitive signal features were selected to train the feed-forward neural networks, which were used for mapping the relationships between process parameters, process conditions and sensor data. A fuzzy controller with initial input/output membership functions and fuzzy rules generated on-line from the trained neural network was applied to perceive process condition changes and make adjustment of process parameters to maintain tool/workpiece contact and energy input. Input/output scaling factors of the fuzzy controller were tuned on-line to improve output response to the amount and trend of control variable deviation from the reference value. Simulation results showed that the presented neuro-fuzzy control scheme has adaptability to process conditions such as parent material and curvature changes, and that the control variables were well regulated. The presented neuro-fuzzy control scheme can be also expected to be applied in other multi-input multi-output machining processes.

Wong Man-Lung. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 99-103). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgments --- p.iii / List of Figures --- p.viii / List of Tables --- p.ix / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Objectives --- p.5 / Chapter 2 --- Cartesian Representation of Membership Function --- p.7 / Chapter 2.1 --- The Cartesian Representation --- p.8 / Chapter 2.2 --- Region of Well-defined Membership Functions --- p.10 / Chapter 2.3 --- Similarity Triangle Interpolation Method --- p.12 / Chapter 2.4 --- The Interpolation Example --- p.18 / Chapter 2.5 --- Further Issues --- p.23 / Chapter 2.6 --- Conclusions --- p.24 / Chapter 3 --- Membership Function as Elements in Function Space --- p.26 / Chapter 3.1 --- L2[0，2] Representation --- p.27 / Chapter 3.2 --- "The Inner Product Space of L2[0,2]" --- p.31 / Chapter 3.3 --- The Similarity Triangle Interpolation Method --- p.32 / Chapter 3.4 --- The Interpolation Example --- p.36 / Chapter 3.5 --- Conclusions --- p.48 / Chapter 4 --- Radius of Influence of Membership Functions --- p.50 / Chapter 4.1 --- Previous Works on Mountain Method --- p.51 / Chapter 4.2 --- Combining Mountain Method and Cartesian Representation --- p.56 / Chapter 4.3 --- Extensibility Function and Weighted-Sum-Averaging Equation --- p.61 / Chapter 4.4 --- Radius of Influence --- p.62 / Chapter 4.5 --- Combining Radius of Influence and Fuzzy Interpolation Technique --- p.64 / Chapter 4.6 --- Model Identification Example --- p.66 / Chapter 4.7 --- Eliminative Extraction --- p.67 / Chapter 4.8 --- Eliminative Extraction Example --- p.70 / Chapter 4.9 --- Conclusions --- p.71 / Chapter 5 --- Fuzzy Inferencing --- p.73 / Chapter 5.1 --- Fuzzy Inferencing and Interpolation in Cartesian Representation --- p.74 / Chapter 5.2 --- Sparse Rule Extraction via Radius of Influence and Elimination --- p.77 / Chapter 5.3 --- Single Input and Single Output Case --- p.78 / Chapter 5.4 --- Multiple Input and Single Output Case --- p.81 / Chapter 5.5 --- Application --- p.89 / Chapter 5.6 --- Conclusions --- p.94 / Chapter 6 --- Conclusions --- p.96 / Appendix --- p.99 / Bibliography --- p.99

No description available.

No description available.

No description available.

Thesis (M.S.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Dept. of Systems Science and Industrial Engineering, 2006. / Includes bibliographical references.

Thesis (M.S.)--Ohio University, March, 1994. / Title from PDF t.p.

Thesis (Ph. D.)--University of Hong Kong, 1998. / Includes bibliographical references (leaves 234-242).