| Author: | Wu, Mengyao |
| Title: | Modeling landmark for indoor and outdoor navigation : a case study on campus |
| Advisors: | Liu, Xin Tao (LSGI) |
| Degree: | M.Sc. |
| Year: | 2019 |
| Subject: | Heat index Temperature measurements Urban climatology -- China - Hong Kong Hong Kong Polytechnic University -- Dissertations |
| Department: | Faculty of Construction and Environment Department of Land Surveying and Geo-Informatics |
| Pages: | ix, 40 pages : color illustrations |
| Language: | English |
| Abstract: | Pedestrian navigation has been a research hotspot topic of location-based service (LBS) in recent years, especially with the popularization of smart mobile devices. Landmarks refer to the fixed, clear and unique objects in regions, which usually can be represented in the form of points of interest that both are visible and identifiable. Compared with the step-by-step procedural wayfinding method, landmark-based wayfinding can reduce the cognitive pressure of pedestrians and improve the efficiency in navigation. This dissertation proposes a saliency quantitative evaluation model for extracting landmarks in indoor environment, and a university campus is selected as study area. This work analyzes the main factors that affect the significance of indoor point of interest (POI) from three aspects: vision, cognition and space, which are used to construct overall saliency quantitative evaluation model for the indoor landmarks. The POI data inside one building in the study is selected for saliency calculation, and landmarks of different levels are extracted and stratified according to saliency, reflecting the indoor spatial knowledge at different scales. The extracted landmarks can be used as important indicators in indoor intelligent navigation systems, providing key clues for fast pathfinding and multi-scale path guidance in complex indoor environments. Based on the extracted indoor and outdoor landmarks, this work generates indoor and outdoor pedestrian networks in the study area. It uses vector CAD floor plan to automatically construct visual relationships between indoor and outdoor buildings and landmarks, which can be applied to establish pedestrian navigation rules and support indoor and outdoor navigation path planning. This method can effectively describe the passage rules of indoor and outdoor pedestrians and meet the real-time requirements of topology network construction, so that it can reduce the pressure on large-scale storage indoor and outdoor road network. Based on this, a multi-target navigation path optimization algorithm is proposed, which has low time cost and can perform path planning in real time. Combining different people's differences in the selection of landmarks, the optimal route for different groups is finally obtained. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022385339803411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.37 MB | Adobe PDF | View/Open |
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/200/10547