Loading...
Search for: odometry
0.005 seconds

    Visual Odometry using RGB-D Cameras

    , M.Sc. Thesis Sharif University of Technology Mohammadi Kaji, Mahsa (Author) ; Kasaei, Shohreh (Supervisor)
    Abstract
    Vision-based localization and 3D orientation estimation of a moving camera, has been for long a vast research area including robot localization and mapping, virtual reality and structure from motion. By introduction of RGB-D cameras in 2010, many sparse methods which are based on key-point extraction and tracking, moved towards dense methods. Dense methods utilize the RGB-D depth and gray-scale values in the images and define the odometry estimation problem as an image registration optimization, without the need to make key-point correspondance in images. Although RGB-D cameras impose specific constraints such as limited depth, depth errors and medium resolution, dense methods have shown... 

    Fusion of Inertial Navigation and Visual Odometry

    , M.Sc. Thesis Sharif University of Technology Aarabi Ardakani, Mohammad Sajjad (Author) ; Sayyadi, Hassan (Supervisor)
    Abstract
    The error of the inertial navigation system increases over time due to the cumulative errors of sensors. Inertial navigation system couples with sensors or other systems to prevent navigation system errors growth. One of the systems that can be used to couple with inertial navigation system is visual odometry. Visual odometry can calculate relative position of the camera at any time and estimate the device path through input images from one camera (Monocular) or multiple cameras (Stereo). Visual odometry algorithms improvements in recent decade cause this system used as real time. In this thesis, DSO algorithm, which is a direct method and monocular approach, couples with an inertial system... 

    Trajectory Estimation of a Vehicle Using Stereo Cameras

    , M.Sc. Thesis Sharif University of Technology Eftekhar, Parham (Author) ; Moghadasi, Reza (Supervisor)
    Abstract
    Visual odometry(VO) is the process of estimating the egomotion of an agent(e.g., vehicle, human, and robot) using the input of a single or multiple cameras attached to it. Application domains include robotics, wearable computing, augmented reality, and automotive. The term was chosen for its similarity to wheel odometry, which incrementally estimates the motion of a vehicle by integrating the number of turns of its wheels over time. Likewise, VO operates by incrementally estimating the pose of the vehicle through examination of the changes that movements induces on the images of its onboard cameras. For the VO to work effectively, there should be sufficient illumination in the environment... 

    Design and Optimization of Positioning System for Hull Crawling Robot

    , M.Sc. Thesis Sharif University of Technology Nasiri, Hamid Reza (Author) ; Khorasanchi, Mahdi (Supervisor) ; Tabeshpour, Mohammad Reza (Supervisor)
    Abstract
    The hulls of various ships are exposed to the problem of biofoulings on the hull after a period of time due to use in the salt water environment of the sea and the existence of suitable conditions for the growth of marine plants, so that the ship after about one month of stopping in the port, in order to start the activity again, it is necessary to clean the hull from these biofoulings. The ship will be transported to the dry dock for cleaning only when it is heavily involved in biofoulings on the hull, and in the meantime, it must be periodically cleaned in water by other systems, including the diver and robotic systems.Using a robotic system to perform this operation has various... 

    Heading angle Observability Enhancement in Visual Inertial Navigation via addition of Magnetometer for GPS Denied Environment

    , M.Sc. Thesis Sharif University of Technology Pahlevani, Ali (Author) ; Pourtakdoust, Hossein (Supervisor)
    Abstract
    In this thesis, a method is presented for improving the observability of the heading angle in a UAV when using the Visual-Inertial navigation algorithm MSCKF by adding a magnetometer sensor. The proposed algorithm serves as a complementary extension to the primary algorithm, and efforts have been made to seamlessly integrate the magnetometer sensor into the primary algorithm to allow for easy modifications to the sensor's characteristics and to observe the resulting output in system simulations. Improving the observability of the heading angle will lead to an enhancement in the overall system state estimation. To achieve this, a new update stage is added to the existing algorithm....