近年來，無人機的應用成為熱門的課題，而空間定位是這些應用的起點。在這篇論文中我們設計了一個以視覺為主的空間定位系統，包含建構模型與定位兩部分。其中建構空間模型這部分，我們採用Structure from Motion (SfM)這種先蒐集影像後建置模型的建模方式，並借助了Changchang Wu設計的軟體VisualSFM。而在空間定位上，我們採用FLANN進行二維特徵點與三維特徵點的匹配的篩選，再使用PnP演算法進行相機位置的計算。在影像特徵擷取的部分，我們使用了SIFT、SURF以及FAST+FREAK三組特徵演算法並比較它們的效能。我們總共在四個場景進行空間模型建置與影像定位的實驗，並且我們採用checking point的方式進行定位的誤差計算。這裡我們以10公分作為定位準確與否的閥值，SIFT演算法在這四個場景都至少有83%的涵蓋率，SIFT演算法至少有65%的涵蓋率，而FAST + FREAK演算法則是至少有60%的涵蓋率。

As the rapid development of drone applications in many field, an accurate method providing positioning is essential. In this thesis, we design a vision-based space positioning system, including the space model construction and positioning. In the space model construction, we use Structure from Motion (SfM) model, which create model after collecting images, and software VisualSFM. In the positioning, we use Fast Library for Approximate Nearest Neighbors (FLANN) to select the inlier points and use Perspective-n-Point (PnP) algorithm to estimate the position of camera. For processing the features of images, three algorithms, Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF) and Features from Accelerated Segment Test (FAST) + Fast Retina Keypoint (FREAK) are used to compare their capabilities. Totally four different scenes are used in our vision-based positioning experiment. Checking points are selected to examine the capabilities of three algorithms with its positioning error in centimeter. Result from each algorithm are discussed and compared based on the processing time and positioning accuracy. Using 10 centimeter as threshold, the experiment result from four scenes show that SIFT could successful positioning at least 83% of the whole space, and SURF could successful positioning at least 65% of the whole space, and FAST + FREAK could successful positioning at least 60% of the whole space.

[1] S. Li, C. Xu, and M. Xie, “A robust o (n) solution to the perspective-n-point problem,”2012 IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 7,pp. 1444–1450, 2012.
[2] V. Lepetit, F. Moreno-Noguer, and P. Fua, “Epnp: An accurate o (n) solution to the pnp problem,” International journal of computer vision, vol. 81, no. 2, pp. 155–166, 2009.
[3] H. Baya, A. Essa, T. Tuytelaarsb, and L. Van Goola, “Speeded-up robust features (surf),” Computer vision and image understanding, vol. 110, no. 3, pp. 346–359, 2008.
[4] E. Rosten and T. Drummond, “Machine learning for high-speed corner detection,” in Computer Vision–ECCV 2006. Springer, 2006, pp. 430–443.
[5] A. Alahi, R. Ortiz, and P. Vandergheynst, “Freak: Fast retina keypoint,” in 2012 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2012, pp. 510–517.
[6] M. S. Svalastog, “Indoor positioning-technologies, services and architectures,” 2007.
[7] Z. Song, G. Jiang, and C. Huang, “A survey on indoor positioning technologies,” in Theoretical and Mathematical Foundations of Computer Science. Springer, 2011, pp. 198–206.
[8] J.-g. Liu, D.-M. Shi, and M. K. Leung, “Indoor navigation system based on omni-directional corridor guidelines,” in 2008 International Conference on Machine Learning and Cybernetics, vol. 3, 2008, pp. 1271–1276.
[9] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International journal of computer vision, vol. 60, no. 2, pp. 91–110, 2004.
[10] C. Wu, “Towards linear-time incremental structure from motion,” in 2013 International Conference on 3D Vision, 2013, pp. 127–134.
[11] C. Wu, S. Agarwal, B. Curless, and S. M. Seitz, “Multicore bundle adjustment,” in 2011 IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 3057–3064.
[12] W. Changchang, “Siftgpu: a gpu implementation of scale invariant feature transform (sift),” 2007)[2013-01]. http://cs.unc.edu/o-ccwu/siftgpu, 2007.
[13] M. Muja and D. G. Lowe, “Scalable nearest neighbor algorithms for high dimensional data,” 2014 IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 11, pp. 2227–2240, 2014.
[14] M. Muja and D. G. Lowe, “Fast matching of binary features,” in 2012 Ninth Conference on Computer and Robot Vision, 2012, pp. 404–410.
[15] M. Muja and D. G. Lowe, “Fast approximate nearest neighbors with automatic algorithm configuration.” VISAPP (1), vol. 2, 2009.
[16] C. Silpa-Anan and R. Hartley, “Optimised kd-trees for fast image descriptor matching,” in 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1–8.
[17] Parrot, “Parrot ar.drone elite edition.” [Online]. Available: http://cdn.ardrone2.parrot.com/
[18] R. Mautz and S. Tilch, “Survey of optical indoor positioning systems,” in 2011 International Conference on Indoor Positioning and Indoor Navigation. IEEE, 2011, pp. 1–7.