如今要使用定位系統時，多數使用全球定位系統(Global Positioning System，通常簡稱GPS)。但是在惡劣天氣、室內寬敞會建築物密集的場地中，GPS信號往往變弱並產生飄移，而基於視覺的定位技術可以在這些條件下提供重要的空間線索。另外，擴增實境技術可以在真實環境中無縫應用虛擬導航。因此，本研究在基於Android系統的應用程式中將視覺式定位與擴增實境相結合，以導引使用者到目的點為目標。
採用詞袋模型與Oriented Fast and Rotated Brief 演算法做模型訓練與比對資料，當使用者在手機端拍攝畫面後再計算出可能的經緯度位置做為視覺式定位，並與GPS做權重計算增加定位準確度。
實驗結果表明本研究所提出的擴增實境導航系統可以幫助使用者定位和識別目的點，例如建築物中的房間或是大廳中的建築雕塑。而相似環境中的比對結果比特殊環境中較差，故本研究適合用於博物館、展覽館等特殊場景居多的環境。

Global Positioning System (GPS) is widely available to discover locations these days. However, GPS signal is weak in bad weather, spacious indoors, or city with crowded high buildings. Alternatively, vision-based positioning technology can provide important spatial clues in these conditions. In addition, Augmented Reality (AR) technology can apply virtual guides in a real environment seamlessly. To this end, we combine visual positioning with AR in an Android-based app to guide people to their targets. Experimental results show that the proposed AR navigation system can help users to locate and identify their target spot such as a room in a building or a sculpture in a hall.

第一章 序論 1
第一節 研究動機 1
第二節 研究目的 1
第三節 論文概述 2
第二章 文獻探討 3
第一節 校園導覽 3
第二節 擴增實境 3
第一項 定義 3
第二項 顯示方式 3
第三項 設備 4
第三節 定位系統 4
第一項 室外定位 4
第二項 室內定位 4
第三項 視覺式定位 5
第四節 Unity遊戲引擎 5
第五節 擴增實境軟體開發套件 5
第一項 ARCore 5
第二項 ARKit 6
第三項 Vuforia 6
第四項 ARToolKit 6
第五項 MapBox 6
第六項 Wikitude 6
第六節 文獻比較 7
第一項 導覽相關文獻比較 7
第二項 定位相關文獻比較 8
第三章 研究方法 11
第一節 系統架構 11
第二節 資料庫 12
第一項 拍攝器材 12
第二項 影片處理 12
第三項 詞袋模型 13
第三節 創建地圖資料 14
第四節 手機APP 16
第一項 虛擬地圖 16
第二項 匯入資料庫 18
第三項 定位功能 19
第四項 導航物件生成 20
第四章 實驗成果 23
第一節 實驗環境 23
第二節 視覺式定位資料庫蒐集 23
第三節 定位精準度 24
第五章 結論 29
第一節 評估與改善 29
第二節 未來工作 29
第三節 總結 29
參考文獻 31

[1]R. T. Azuma, "A Survey of Augmented Reality," Presence: Teleoperators and Virtual Environments, vol. 6, no. 4, pp. 355-385, 1997.
[2]P. K. J. I. J. o. W. I. N. Enge, "The global positioning system: Signals, measurements, and performance," International Journal of Wireless Information Networks, vol. 1, no. 2, pp. 83-105, 1994.
[3]K. Al Nuaimi and H. Kamel, "A survey of indoor positioning systems and algorithms," in 2011 international conference on innovations in information technology, 2011, pp. 185-190: IEEE.
[4]R. Huitl, G. Schroth, S. Hilsenbeck, F. Schweiger, and E. Steinbach, "TUMindoor: An extensive image and point cloud dataset for visual indoor localization and mapping," in 2012 19th IEEE International Conference on Image Processing, 2012, pp. 1773-1776: IEEE.
[5]S. Se, D. G. Lowe, and J. J. Little, "Vision-based global localization and mapping for mobile robots," IEEE Transactions on Robotics, vol. 21, no. 3, pp. 364-375, 2005.
[6]T. Reinhardt. (2019). Using Global Localization to Improve Navigation [Internet]. Available: https://ai.googleblog.com/2019/02/using-global-localization-to-improve.html
[7]Y. Xia, C. Xiu, and D. Yang, "Visual indoor positioning method using image database," in 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS), 2018, pp. 1-8: IEEE.
[8]H. Subakti and J.-R. Jiang, "A marker-based cyber-physical augmented-reality indoor guidance system for smart campuses," in 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), 2016, pp. 1373-1379: IEEE.
[9]K.-M. Yu, J.-C. Chiu, M.-G. Lee, and S.-S. Chi, "A mobile application for an ecological campus navigation system using augmented reality," in 2015 8th International Conference on Ubi-Media Computing (UMEDIA), 2015, pp. 17-22: IEEE.
[10]L. Wu and X. Yu, "Outdoor Navigation with Handheld Augmented Reality," in 2018 International Conference on Audio, Language and Image Processing (ICALIP), 2018, pp. 237-241: IEEE.
[11]M. Zaifri, A. Azough, and S. O. El Alaoui, "Experimentation of visual augmented reality for visiting the historical monuments of the medina of Fez," in 2018 International Conference on Intelligent Systems and Computer Vision (ISCV), 2018, pp. 1-4: IEEE.
[12]C. Yang and H.-R. Shao, "WiFi-based indoor positioning," IEEE Communications Magazine, vol. 53, no. 3, pp. 150-157, 2015.
[13]C. Feng, W. S. A. Au, S. Valaee, and Z. Tan, "Received-signal-strength-based indoor positioning using compressive sensing," IEEE Transactions on mobile computing, vol. 11, no. 12, pp. 1983-1993, 2011.
[14]S. Xu, W. Chou, and H. J. S. Dong, "A robust indoor localization system integrating visual localization aided by CNN-based image retrieval with Monte Carlo localization," Sensors, vol. 19, no. 2, p. 249, 2019.
[15]J. Einsiedler, D. Becker, and I. Radusch, "External visual positioning system for enclosed carparks," in 2014 11th Workshop on Positioning, Navigation and Communication (WPNC), 2014, pp. 1-6: IEEE.
[16]A. Iriarte-Solis, P. González-Villegas, R. Fuentes-Covarrubias, and G. Fuentes-Covarrubias, "Mobile Guide to Augmented Reality for Campus of the Autonomous University of Nayarit," in 2016 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct), 2016, pp. 1-4: IEEE.
[17]B. Al Delail, L. Weruaga, and M. J. Zemerly, "CAViAR: Context aware visual indoor augmented reality for a university campus," in 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, 2012, vol. 3, pp. 286-290: IEEE.
[18]H. Xue, L. Ma, and X. Tan, "A fast visual map building method using video stream for visual-based indoor localization," in 2016 International Wireless Communications and Mobile Computing Conference (IWCMC), 2016, pp. 650-654: IEEE.
[19]E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in 2011 International conference on computer vision, 2011, pp. 2564-2571: IEEE.