全球衛星定位系統(Global Positioning System, GPS)在我們的日常生活中扮演了重要的角色，而近年來隨著電腦視覺的同步發展，定位系統已不再侷限以地圖方式呈現，本論文希望藉由使用者所拍攝之影像來獲得目標物的三維座標。
為此目的，本論文提出一套影像興趣點(Point Of Interest, POI)之三維定位系統，為了提高定位的精確度，本系統整合了GPS定位以及Google圖資來分析興趣點資訊，使用者僅需輸入一張影像，並透過尺度不變特徵轉換演算法(Scale-Invariant Feature Transform, SIFT)與範圍內的每一張街景影像進行特徵比對來找出適合的參考點，再經由衛星影像來改善GPS精確度問題，便能利用三角測量推斷出使用者視線範圍內之目標物的三維座標。
本系統經過多組平面座標測量與高度測量之實驗評估後，平面座標測量精度平均可達1.013公尺、均方根誤差為1.029公尺；而高度測量精度平均可達0.962公尺、均方根誤差為1.329公尺。

The global positioning system plays an important role in our daily life. In recent years, with the rapid development of computer vision, the positioning system can be used in a quite different way. In this thesis, the goal is to obtain the three-dimensional coordinate of the target object through an image taken by a user.
To achieve our goal, this paper proposes a three-dimensional positioning system for the point of interest in an image. In order to improve the accuracy of positioning, the system integrates GPS position and Google map data to obtain the information of the point of interest. Users only need to input an image and match it with the street view images from neighboring positions by the SIFT algorithm to find two suitable reference points. Then we improve the GPS accuracy by analyzing satellite images. Finally, we can infer the three-dimensional coordinate of the target within the user's sight by triangulation.
We have conducted experiments using several known points to achieve horizontal precision of 1.013m and 1.029m in terms of root-mean-square error and vertical precision of 0.962m and 1.329m in terms of root-mean-square error.

[1] Aicam. https://www.lg.com.
[2] Googlelens. https://lens.google.com.
[3] Peakfinder. https://www.peakfinder.org.
[4] Terrago. https://terragotech.com.
[5] Kai-Hsiang Chen, Chi-Ruo Wu, Yue-Lin Yang, Jen-Wei Huang, and Tsung-Yi Ho. Efficient building identification using structural and spatial information on mobile devices. IEEE International Conference on Multimedia and Expo Workshops, pages 1-5, 2014.
[6] Martin A. Fischler and Robert C. Bolles. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, pages 381-395, 1981.
[7] Aditi Gupta and Vibhor Harit. Child safety & tracking management system by using gps, geo-fencing & android application: An analysis. 2nd International Conference on Computational Intelligence and Communication Technology, pages 683-686, 2016.
[8] Bruce R. Harvey. Survey computations. Survey Geospatial Engineering, School of Civil Environmental Engineering. The University of New South Wales, pages 49-50, 2012.
[9] Tao He, Yong Wei, Zhijun Liu, Guorong Qing, and Defen Zhang. Content based image retrieval method based on sift feature. 3rd International Conference on Intelligent Transportation, Big Data and Smart City, pages 649-652, 2018.
[10] Shiuan Huang and Hsueh-Ming Hang. Multi-query image retrieval using cnn and sift features. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, pages 1026-1034, 2017.
[11] Chia-Hsiang Lee, Yu-Chi Su, and Liang-Gee Chen. Accurate positioning system based on street view recognition. IEEE International Conference on Acoustics, Speech and Signal Processing, pages 2305-2308, 2012.
[12] David G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, pages 91-110, 2004.
[13] Mahdi Salarian, Nick Ileiv, and Rashid Ansari. Accurate image based localization by applying sfm and coordinate system registration. IEEE International Symposium on Multimedia, pages 189-192, 2017.
[14] Wei Shao, Youjing Zhang, Lingling Wang, Liwen Chen, and Zhiqi Qian. Extraction building based on adaptive detection algorithm of key points. IEEE 19th International Conference on Geoinformatics, pages 1-4, 2011.
[15] Victor J.D. Tsai and Chun-Ting Chang. Three-dimensional positioning from google street view panoramas. IET Image Processing, pages 229-239, 2013.
[16] Di-Kai Yang, Yu-Wen Lin, Yi-I Chiu, Pau-Choo Chung, and Chun-Rong Huang. Vision based campus guide system on intelligent mobile phone. IEEE International Conference on Multimedia and Expo Workshops, pages 1-6, 2013.