| Author: | Lee, Max Jwo Lem |
| Title: | Integration of camera-based localization frameworks and building information modeling for improved indoor-outdoor positioning accuracy |
| Advisors: | Hsu, Li-ta (AAE) |
| Degree: | Ph.D. |
| Year: | 2025 |
| Subject: | Indoor positioning systems (Wireless localization) Building information modeling Computer vision Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Aeronautical and Aviation Engineering |
| Pages: | xxi, 148 pages : color illustrations |
| Language: | English |
| Abstract: | This dissertation addresses seamless positioning across indoor and outdoor environments where GNSS fails, through the integration of camera-based localization frameworks and Building Information Modeling (BIM) using semantic understanding as the bridge between them. The research answers four central questions through interconnected frameworks progressing from foundational semantic understanding to sophisticated multi-modal positioning systems. Research Question 1 investigates whether environmental semantics enable AR-grade positioning without expensive infrastructure. Progressive improvement from smartphone material-based positioning (7.74m) to panorama-based differential rendering (0.84m) achieves 90% accuracy improvement through 360-degree capture and Level-of-Detail-aware optimization. Research Question 2 addresses continuous tracking for mobile AR navigation through Extended Kalman Filter integration of semantic visual positioning with visual-inertial odometry, achieving 0.69m accuracy at 10Hz with graceful degradation. Research Question 3 tackles scale ambiguity in Structure-from-Motion through Generalized Procrustes Analysis, combining BIM’s global positioning with photogrammetric relative accuracy to achieve 0.59m positioning with recovered metric scale. Research Question 4 validates BIM-integrated frameworks for digital twin applications through a three-stage pipeline achieving 0.47m panorama and 0.92m smartphone positioning, removing the need for point cloud mapping while maintaining real-time efficiency. The research establishes five theoretical contributions: semantic-aware positioning theory, multi-modal integration architectures, scale-aware photogrammetric integration, adaptive environmental modeling, and cross-environment positioning continuity. These contributions provide foundations for smart cities, autonomous navigation systems, and immersive digital environments. |
| Rights: | All rights reserved |
| Access: | open access |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/14326