A PDR-Based 3D Indoor Localization System With Landmarks Detection
Doctoral Thesis
Đã lưu trong:
| Tác giả chính: | |
|---|---|
| Định dạng: | Dissertation |
| Ngôn ngữ: | English |
| Được phát hành: |
Hallym University
2023
|
| Những chủ đề: | |
| Truy cập trực tuyến: | https://scholar.dlu.edu.vn/thuvienso/handle/DLU123456789/116232 |
| Các nhãn: |
Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!
|
| Thư viện lưu trữ: | Thư viện Trường Đại học Đà Lạt |
|---|
| id |
oai:scholar.dlu.edu.vn:DLU123456789-116232 |
|---|---|
| record_format |
dspace |
| spelling |
oai:scholar.dlu.edu.vn:DLU123456789-1162322023-10-05T16:57:29Z A PDR-Based 3D Indoor Localization System With Landmarks Detection Nguyễn, Hữu Khánh Smartphone PDR Inertial sensor Landmarks Doctoral Thesis Due to the high demand of location-based services in buildings, various indoor positioning methods have been proposed. Among them, the Pedestrian Dead Reckoning (PDR) systems have received much attention due to the widespread deployment of mobile devices such as smartphones or tablets and no requirement of infrastructure. In this dissertation, I focus on improving the performance of the traditional PDR using smartphones to track the position of a pedestrian holding these devices while he/she walks in a building. However, the traditional PDR system is subject to cumulative errors caused by the limitation of the integrated sensors of the smartphone. Therefore, to overcome the limitation, different kinds of methods are researched and implemented. First of all, I proposed effective methods for accurately detecting the number of walking steps, estimating the step length adaptively, and estimating the heading direction using the set of inertial sensors of a smartphone. The proposed walking behavior recognition method can be used as an important functional block in a PDR system. I have developed methods for classifying the four main holding styles while walking, i.e., holding a phone in the hand while watching it, holding a phone while calling, swinging it, and putting it in a pocket. The four main holding styles are divided into 34 sub-styles, which encompass the various free styles of holding a smartphone during daily activities. This classification makes the user more convenient while walking in indoor environments. Therefore, I obtained better performance when counting the walking steps, estimating the step length, and estimating the heading direction, although I only employ a set of feature values that are easily calculated without any complex data processing techniques. Secondly, to reduce the inevitable accumulated error over time, I suggested a method of using location related information from environments. I named it ‘landmark’, which is defined as a specific area (or point) where the pedestrian passes by in a building such as a door, a corner or a crossroad. If the system detects a landmark during the walking period, it will correct the position of the user with the pre-defined position information of the landmark. In this work, I proposed different kinds of landmarks such as radio landmark, turning landmark, and stairs landmark. I have developed methods to detect the landmarks only using the sensors embedded in smartphones. Moreover, by using the combination of WiFi and barometer, the current user’s floor is provided. This information then merges with the two-dimensional position from the PDR to build the multi-floor navigation system. Based on numerous experiments, the excellent performance of the proposed method was demonstrated. The proposed scheme only requires the smartphone with integrated sensors to work without any external devices and contributes to lowering on the error rate of positioning results, less than 77.29% compared to the original PDR system. The under 2-m error between the true and estimated ending points could be achieved. 2023-08-12T13:37:23Z 2023-08-12T13:37:23Z 2018 Dissertation https://scholar.dlu.edu.vn/thuvienso/handle/DLU123456789/116232 en application/pdf Hallym University |
| institution |
Thư viện Trường Đại học Đà Lạt |
| collection |
Thư viện số |
| language |
English |
| topic |
Smartphone PDR Inertial sensor Landmarks |
| spellingShingle |
Smartphone PDR Inertial sensor Landmarks Nguyễn, Hữu Khánh A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| description |
Doctoral Thesis |
| format |
Dissertation |
| author |
Nguyễn, Hữu Khánh |
| author_facet |
Nguyễn, Hữu Khánh |
| author_sort |
Nguyễn, Hữu Khánh |
| title |
A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| title_short |
A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| title_full |
A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| title_fullStr |
A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| title_full_unstemmed |
A PDR-Based 3D Indoor Localization System With Landmarks Detection |
| title_sort |
pdr-based 3d indoor localization system with landmarks detection |
| publisher |
Hallym University |
| publishDate |
2023 |
| url |
https://scholar.dlu.edu.vn/thuvienso/handle/DLU123456789/116232 |
| _version_ |
1779410500805722112 |