Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/93583
PIRA download icon_1.1View/Download Full Text
Title: A feasibility study on smartphone localization using image registration with segmented 3D building models based on multi-material classes
Authors: Lee, MJL 
Hsu, LT 
Issue Date: 2021
Source: Proceedings of the 2021 International Technical Meeting of The Institute of Navigation, January 2021, p. 317-323
Abstract: Accurate smartphone-based outdoor localization system in deep urban canyons are increasingly needed for various IoT applications such as augmented reality, intelligent transportation, etc. This article proposes a multi-material image registration solution for accurate pose estimation in urban canyons where global navigation satellite system (GNSS) tends to fail. In the offline stage, a material segmented city model is used to generate segmented images at each pose (six degrees of freedom of position and rotation). In the online stage, an image is taken with a smartphone camera that provides textual information about the surrounding environment. The approach utilizes computer vision algorithms to rectify and manually segment between the different types of material identified in the smartphone image. The hypothesized poses (candidate) images are then matched with the segmented smartphone image. The candidate image with the maximum likelihood is regarded as the estimated pose of the user. The positioning results achieves 2.0m level accuracy in common high rise along street, 5.5m in foliage dense environment and 15.7m in alleyway. A 45% positioning improvement to current state-of-the-art method. The estimation of yaw achieves 2.3° level accuracy, 8 times the improvement to smartphone IMU.
Publisher: Institute of Navigation
ISBN: 9781713827009
171382700X
DOI: 10.33012/2021.17836
Description: 2021 International Technical Meeting of The Institute of Navigation, January 25 - 28, 2021, online
Rights: Posted with permission of the author.
The following publication Lee, Max Jwo Lem, Hsu, Li-Ta, "A Feasibility Study on Smartphone Localization using Image Registration with Segmented 3D Building Models based on Multi-Material Classes," Proceedings of the 2021 International Technical Meeting of The Institute of Navigation, January 2021, pp. 317-323 is first published by the Institute of Navigation and is available at https://doi.org/10.33012/2021.17836.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
Lee_Feasibility_Study_Smartphone.pdf837.19 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

67
Last Week
0
Last month
Citations as of Jan 5, 2025

Downloads

72
Citations as of Jan 5, 2025

SCOPUSTM   
Citations

2
Citations as of Jan 9, 2025

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.