The goal of this thesis is to present a heuristic that mitigates the positioning degradation in urban canyons by identifying NLOS signals using fish-eye images and remove them from the final positioning calculation.Using a wide angle camera pointed towards the sky we can record the environment and detect the open sky region and different categories of obstacles.Than the satellites are projected onto the segmented image and detect NLOS signals that are obstructed by the obstacles.The thesis descr... 

【文章來源】：上海交通大學(xué)上海市 211工程院校 985工程院校 教育部直屬院校

【文章頁數(shù)】：87 頁

【學(xué)位級(jí)別】：碩士

【文章目錄】：
abstract
Chapter 1 Introduction
    1.1 Project Context
    1.2 Requirements
    1.3 Project Objectives and Specifications
        1.3.1 Collection of image data,GNSS data and IMU data
        1.3.2 Process the image data
        1.3.3 Rejection list creation based on the generated masks
Chapter 2 State of the art
    2.1 Image Segmentation Methods
        2.1.1 Classical Image processing
        2.1.2 Classical Machine Learning
        2.1.3 Deep Learning
    2.2 NLOS Mitigation Techniques
        2.2.1 NLOS signal exclusion
        2.2.2 NLOS signal weighting
        2.2.3 NLOS signal correction
Chapter 3 Theoretical Foundation
    3.1 Data Module
        3.1.1 Necessary Devices
        3.1.2 Collected Signals
        3.1.3 Data Structure
        3.1.4 Synchronization heuristic
    3.2 Obstacle detection Module
        3.2.1 Pre-Processing of image data
        3.2.2 Image Segmentation
        3.2.3 Post-processing of image data
    3.3 NLOS Projection and Detection Module
        3.3.1 Coordinates transformation
        3.3.2 Satellite Detection
Chapter 4 Detailed Design and Implementation
    4.1 Data Module
        4.1.1 Necessary Devices
        4.1.2 Data Collection and Synchronization
    4.2 Obstacle Detection Module
        4.2.1 Pre-Processing of Image Data
        4.2.2 Image Segmentation
        4.2.3 Post-processing of Image Data
    4.3 NLOS Projection and Detection Module
        4.3.1 Coordinates transformation and projection
        4.3.2 NLOS detection and visibility list creation
Chapter 5 Results
    5.1 Data Collection and Synchronization Results
    5.2 Image segmentation Results
        5.2.1 Pre-processing
        5.2.2 Image segmentation
        5.2.3 Post-processing
    5.3 NLOS detection Results
Chapter 6 Conclusion
    6.1 Summary
    6.2 Results discussion
    6.3 Future work
Appendix A Set up
    A.1 Collection Software
    A.2 Obstacle Detection Software
    A.3 NLOS detection and rejection Software
Appendix B Additional theoretical aspects
    B.1 Obstacle detection Module
List of Abbreviations
Bibliography
Resume



本文編號(hào)：3460575