跳到主要內容

臺灣博碩士論文加值系統

(44.192.48.196) 您好!臺灣時間:2024/06/16 10:49
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:高識鈞
論文名稱(外文):An Indoor Positioning System Based on Tiles
指導教授:黃啟富
指導教授(外文):HUANG, CHI-FU
口試委員:林國祥陳烈武黃啟富
口試委員(外文):LIN, GUO-SHIANGCHEN, LIEN-WUHUANG, CHI-FU
口試日期:2020-07-29
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:37
中文關鍵詞:室內定位影像識別
外文關鍵詞:Indoor PositioningImage Recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:253
  • 評分評分:
  • 下載下載:3
  • 收藏至我的研究室書目清單書目收藏:0
位置信息是人們日常生活中必不可少的信息之一。它對於許多應用程序都是必不可少的,例如路徑規劃,醫療保健,人身安全,導航和機器人等。有了精確的定位系統,人們的生活不僅能更加方便也能更加安全。在室外環境,我們可以直接利用GPS獲取當期的位置訊息;然而在室內環境,由於建築物的遮蔽效應將會導致GPS的訊號無法接收,因此室內無法使用GPS。在過去的文獻中,已經提出了許多室內定位系統,其可能遭受信號不穩定或維護成本高的困擾。在本文中,我們提出了一種基於磁磚的室內定位系統。初步實驗測試了將磁磚用於室內定位地標的可行性,它具有獨特的花紋並在建築物中具備高度的覆蓋率,並且其花紋比起無線訊號更能抵抗動態環境的變化。在提出的系統中,管理員首先收集磁磚的圖像以提取其特徵。這些特徵將與磁磚的位置訊息對應,以此建立了用於進一步位置查詢的資料庫。當使用者在未知位置時,他只需拍攝附近磁磚的照片。通過查詢資料庫,使用者將可以獲得其位置。為了進一步提高系統的可靠性和有效性,我們設計了幾種方法來控製磁磚圖像的品質。在理想環境下的平均圖像識別率是100%。此外,我們開發了一種影像裁切程序,以將識別所花費的時間減少73%。
Location information is one of the essential information for people’s daily life. It is indispensable for many applications, such as path planning, medical care, personal security, navigation, robots, etc. With an accurate positioning system, people’s lives can be more convenient and safer. Not likely outdoors, where we can obtain location information directly, GPS is not available indoors due to the shadowing effect of the building. In literature, many indoor positioning system have been proposed, which may suffer from unstable signals or high maintenance costs. In this paper, we suggest an indoor positioning system based on the floor tiles. Preliminary experiments tested the feasibility of tiles as indoor positioning landmarks, it have unique patterns and high coverage in the buildings, and its patterns are more resistant to the dynamic environment than wireless signals. In the proposed system, the administrator first collects the images of tiles to extract their features. Those features, together with position information of tiles, establish a database for further position inquiry. When a user is at an unknown location, he only needs to take a picture of a nearby tile. By quiring the database, the user can obtain his position. To further increase the reliability and effectiveness of our system, we design several approaches to control the quality of tile images. The average of image recognition rate in an ideal environment is 100%. Besides, we developed an image cropping process to reduce the time consumption on recognition by 73%.
I. Introduction 1
II. Related Work 5
A. Wi-Fi 5
B. Geomagnetism 6
C. Bluetooth 6
D. Visible Light 7
E. Vision 7
III. Preliminary 8
A. Tile Pattern Uniqueness 8
B. Feature Robustness 9
a. Ambient Light 10
b. The Angle of Camera 11
c. The Orientation of Camera 12
d. The mix of the listed factors 14
IV. System Design 16
A. System Architecture 16
B. Indoor Floor Plan 17
C. Feature Database 17
D. Feature Extraction Algorithm 17
E. Data Gathering 18
a. Camera 18
b. Accelerometer 18
c. Magnetometer 19
F. Image Assessment 19
a. Image Quality Constraint 20
b. Camera Angle Constraint 20
G. Preprocessing 21
a. Orientation Correction 21
b. Denoise 22
H. Image Cropping 23
V. Experiments 26
A. Setup 26
B. Uniqueness of Database 27
C. Feasibility of System 27
D. The Optimal Kernel Size of Image Smoothing 28
E. The Optimal Number of Features 29
F. Image Cropping 31
VI. Conclusion 34
VII. References 35


[1]Z. Li, X. Zhao, Z. Zhao, F. Hu, H. Liang, and T. Braun, “Crowdsensing indoor walking paths with massive noisy crowdsourcing user traces,” IEEE Global Communications Conference (GLOBECOM), 2018.
[2]E. Park, J. H. Kim, H. S. Nam, and H.-J. Chang, “Requirement analysis and implementation of smart emergency medical services,” IEEE Access, vol. 6, pp. 42022-42029, 2018.
[3]B. Li, J. P. Munoz, X. Rong, Q. Chen, J. Xiao, Y. Tian, A. Arditi, and M. Yousuf, “Vision-based mobile indoor assistive navigation aid for blind people,” IEEE Transactions on Mobile Computing, vol. 18, no. 3, pp. 702-714, 2018.
[4]J. Dong, M. Noreikis, Y. Xiao, and A. Ylä-Jääski, “ViNav: A vision-based indoor navigation system for smartphones,” IEEE Transactions on Mobile Computing, vol. 18, no. 6, pp. 1461-1475, 2018.
[5]Q. Fu, H. Yu, L. Lai, J. Wang, X. Peng, W. Sun, and M. Sun, “A robust RGB-D SLAM system with points and lines for low texture indoor environments,” IEEE Sensors Journal, vol. 19, no. 21, pp. 9908-9920, 2019.
[6]A. P. Jones, “Indoor air quality and health,” Atmospheric Environment, vol. 33, no. 28, pp. 4535-4564, 1999.
[7]Q. Song, S. Guo, X. Liu, and Y. Yang, “CSI amplitude fingerprinting-based NB-IoT indoor localization,” IEEE Internet of Things Journal, vol. 5, no. 3, pp. 1494-1504, 2017.
[8]E. Leitinger, F. Meyer, F. Hlawatsch, K. Witrisal, F. Tufvesson, and M. Z. Win, “A belief propagation algorithm for multipath-based SLAM,” IEEE Transactions on Wireless Communications, vol. 18, no. 12, pp. 5613-5629, 2019.
[9]M. Fazelinia, M. R. Daliri, and S. Ebadollahi, “Wi-Fi RSS-based Indoor Localization Using Reduced Features Second Order Discriminant Function,” IEEE Iranian Conference on Electrical Engineering (ICEE), 2019.
[10]H. D. Abdulkarim, and H. Sarhang, “Normalizing RSS Values of Wi-Fi Access Points to Improve an Integrated Indoors Smartphone Positioning Solutions,” IEEE International Engineering Conference (IEC), 2019.
[11]X. Wang, X. Wang, and S. Mao, “CiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi,” IEEE International Conference on Communications (ICC), 2017.
[12]C. Park, and S. H. Rhee, “Indoor positioning using Wi-Fi fingerprint with signal clustering,” IEEE International Conference on Information and Communication Technology Convergence (ICTC), 2017.
[13]I. M. Özçelik, and M. Y. Dönmez, “A Wi-Fi fingerprinting-based indoor localization approach: M-Weighted position estimation (m-WPE),” IEEE Signal Processing and Communications Applications Conference (SIU), 2017.
[14]A. Moreira, I. Silva, F. Meneses, M. J. Nicolau, C. Pendao, and J. Torres-Sospedra, “Multiple simultaneous Wi-Fi measurements in fingerprinting indoor positioning,” IEEE International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2017.
[15]M. Khan, Y. D. Kai, and H. U. Gul, “Indoor Wi-Fi positioning algorithm based on combination of location fingerprint and unscented Kalman filter,” IEEE International Bhurban Conference on Applied Sciences and Technology (IBCAST), 2017.
[16]N. Lee, and D. Han, “Magnetic indoor positioning system using deep neural network,” IEEE International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2017.
[17]S. Chen, D. Chen, Y. Wang, and Y. Wu, “GR-PMS: A geomagnetism-based real-time positioning mechanism of smart phones,” IEEE International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2018.
[18]H. J. Bae, and L. Choi, “Large-Scale Indoor Positioning using Geomagnetic Field with Deep Neural Networks,” IEEE International Conference on Communications (ICC), 2019.
[19]Q. H. Nguyen, P. Johnson, T. T. Nguyen, and M. Randles, “Optimized indoor positioning for static mode smart devices using BLE,” IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), 2017.
[20]S. G. Obreja, T. Aboul-Hassna, F. D. Mocanu, and A. Vulpe, “Indoor localization using radio beacon technology,” IEEE International Symposium on Electronics and Telecommunications (ISETC), 2018.
[21]X. Wu, R. Shen, L. Fu, X. Tian, P. Liu, and X. Wang, “iBILL: Using iBeacon and inertial sensors for accurate indoor localization in large open areas,” IEEE Access, vol. 5, pp. 14589-14599, 2017.
[22]T. Wenge, M.-T. Chew, F. Alam, and G. S. Gupta, “Implementation of a visible light based indoor localization system,” IEEE Sensors Applications Symposium (SAS), 2018.
[23]B. Zhu, J. Cheng, Y. Wang, J. Yan, and J. Wang, “Three-dimensional VLC positioning based on angle difference of arrival with arbitrary tilting angle of receiver,” IEEE Journal on Selected Areas in Communications, vol. 36, no. 1, pp. 8-22, 2017.
[24]L. Árvai, and G. Dobos, “On demand vison-based indoor localization,” IEEE International Carpathian Control Conference (ICCC), 2019.
[25]J. Noonan, H. Rotstein, A. Geva, and E. Rivlin, “Vision-Based Indoor Positioning of a Robotic Vehicle with a Floorplan,” IEEE International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2018.
[26]A. Xiao, R. Chen, D. Wu, and Y. Chen, “Positioning in Large Indoor Spaces using Smartphone Camera based on Static Objects,” IEEE Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS), 2018.
[27]T. Lindeberg, “Scale invariant feature transform,” 2012.
[28]H. Bay, T. Tuytelaars, and L. Van Gool, “Surf: Speeded up robust features,” European Conference on Computer Vision, 2006.
[29]E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” IEEE International Conference on Computer Vision, 2011.
[30]J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, no. 6, pp. 679-698, 1986.
[31]T. Ferreira, and W. Rasband, “ImageJ user guide,” ImageJ/Fiji, vol. 1, pp. 155-161, 2012.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top