Sharif Digital Repository

The research field of localization with high precision (precision of 10 micrometers) has greatly attracted attentions in recent years. Optical flow sensor is one of the inexpensive solutions for the localization of robot, which have been used in computer mice. The most important application of this thesis is to localize walking micro robot. The main challenge of previous research is the fact that sensor's precision is highly dependent on the surface texture. The aim of this research is to implement an appropriate algorithm on optical flow sensor in order to increase the robustness of sensor's precision to surface texture. In this regard, firstly experimental hardware has been designed and... 

This thesis represents the obstacle avoidance of a fixed-wing small aircraft using optical flow information of cameras mounted on the aircraft. The thesis consists of two main sections. In section one, the ideal optical flow has been simulated based on the camera model, complete six DOF of flight equations, and the geometry of the environment. An analytical formula has been derived to relate the obstacle detection distance to the maneuverability of the aircraft. Having the obstacle detection distance, the control and navigation algorithms have been developed to achieve a collision-free flight for the aircraft in urban canyons and junctions. The effect of some parameters such as approach... 

Robot navigation and guidance is an important issue in robotic. Navigation by itself includes localization, path planning and guidance. For having a successful navigation it is necessary to succeed in all of those parts. The localization precision as basic part of localization is important and having more accurate information of robot position is important. Recently, sensors which use optical flow technic and are widely used in optical mouses are so common and they are able to measure displacement with resolution of 3 to 63 micron. In this research, a localization method for micro robot localization based on optical flow and INS sensor data fusion is presented.
Two data fusion method... 

Attitude estimation means calculating the state variables during the flight, especially in landing and takeoff phases. If we can extract the optical flow using the sensors mounted on the flying object, due to the fact that the optical flow is created by linear and rotational speed of the object relative to the surrounding, we are able to calculate the relative attitude by analyzing the optical flow. Indeed the purpose is developing this idea by using artificial neural networks.
First, we find the optical flow patterns for every attitude condition near the ground, using geometrical calculations. Then we produce an optimal neural network by these patterns. This network has the ability to... 

The goal of this thesis is to carry out an investigation on appropriate image processing algorithms suitable for the use in parafoil-payload guidance as low-cost methods. The image-based navigation algorithms are first classified, and then methods of parafoil guidance are proposed. A mathematical model of camera is presented in order to show the relationship between 2D image and 3D real world for image simulation in the loop. The featurs point selection and tracking as the first step of image-based navigation has been examined in this study. Feature points tracking has been done in two way, based on optical flow and template matching methods. Based on the result obtained after... 

This research focuses on the robust mobile robot localization exploiting motion information acquired from an optical mouse operating based on optical flow technology. Most techniques of visual motion measurement are based on the well research discipline called “optical flow”. Theoretically, optical flow as a method of localization can be highly accurate, but it is sensitive to the noise and surface texture/optical characteristics and distance variations between the CCD detector and surface. As one could not achieve acceptable results in practical situations, to handle these problems, we propose to attach an acceleration – gyro (INS) sensor on the CCD detector (optical mouse) to improve the... 

In this study a variational framework for joint segmentation and motion estimation is provided for inspecting heart in Cine MRI sequences. In the first work, a functional including Mumford-Shah segmentation and optical flow based dense motion estimation is proposed. However, the motion estimation technique is replaced with warping estimation in the second work to reach in more regular and smooth motion field based on tracking of cardiac boundaries. Both of these functionals are then approximated by using the phase-field method to make them suitable for extracting Euler-Lagrange equations. Numerical solution to the optimization problem, when the time and image spaces are discretized by finite... 

In recent years, steering percutaneous needle insertions with the aid of soft tissue modeling techniques has been of great interest. In this thesis an optical flow based motion estimation method is used to estimate tissue deformation. It also addresses needle tracking in ultrasound images for prostate biopsy and brachytherapy. The thesis reviews reported methods on needle insertion using ultrasound imagery and further introduces a projection based method (Hough Transform) for needle tracking. Considering that ultrasound images have releatively low contrast and high speckle noise content, diffusion and wavelet-based filtering methods are employed as noise reduction techniques. Next, an... 

In this research, inspired by the navigation system of insects, a method for extracting the navigation information required for an autonomous device is presented, with an information input section in the form of image processing using optical flow and an information processing section with an artificial brain structure. In this method, the information obtained from the optical flow is processed by the neural network structure and the navigation information needed to control and guide the autonomous device is obtained. There are several methods to estimate the optical flow between two frames, in this research, the DEQ-Flow optical flow estimation network, which is a method based on deep... 

Inspection of confined corridors is one of the important and necessary topics in various industries, including mines, oil and gas industries. Human inspection is very time-consuming and expensive due to the difficulty of accessing these environment, and in some corridors, it is not possible to inspect at all. In this thesis, UAV guidance and navigation algorithms have been developed by using informations got from optical flow, inertial and ultrasonic sensors, so that the UAV can fly automatically inside the confined corridor without colliding the boundaries. At first, a model of the space around the corridor, UAV and its subsystems has been proposed so that we can use it to create a...