研究生: |
胡皓翔 Hao-hsiang Hu |
---|---|
論文名稱: |
運用街景影像資料庫的智慧手機定位 Smartphone Positioning with Street View Image Database |
指導教授: |
高維文
Wei-wen Kao |
口試委員: |
張淑淨
none 徐繼聖 none |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2013 |
畢業學年度: | 101 |
語文別: | 中文 |
論文頁數: | 93 |
中文關鍵詞: | 影像定位 、影像比對 、街景 、卡爾曼濾波器 |
外文關鍵詞: | Image positioning, Image matching, Street View database, Kalman filtering |
相關次數: | 點閱:164 下載:3 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
目前在導航定位方面,有許多的研究與方法,像是使用GPS 、雷射、加速規、陀螺儀等各種感測器。但是每個感測器都有其限制,因此我們採取一種搭配街景(Street View)的影像定位方式,使用的工具是目前已經普及化的智慧型手機。
本論文利用影像匹配的概念做出影像定位,我們將建立一個影像的資料庫,裡面包含了位置與方向等各種資訊,另一方面透過手機或者各種相機鏡頭拍攝當前場景,將拍攝到的影像與建立好的影像資料庫進行比對,決定出相似度高的照片,並且進行位置的估算,最後搭配行人方位推估法,經由卡爾曼濾波器進行路徑的校正,達到一個優良的定位效果。
There have been various methods and research on navigation such as using global position system (GPS), accelerometer and gyroscope. However, those sensors possess limitations. In this thesis a new approach which combines street view image database with real-time image from a smart phone for positioning is developed.
This thesis proposes a concept of image matching to generate image
positioning. An image database with information such as photo position and direction is built up to cover a territory. An image of current location is obtained via a smart phone or a camera and is compared with the image
database to select database images with the highest similarities. By estimating the position and correcting the path using pedestrian dead reckoning (PDR) and Kalman filter (KF), the experimental results show a higher navigation accuracy.
[1] H. Durrant-Whyte and T. Bailey, “Simultaneous Localisation and Mapping (SLAM):Part I The Essential Algorithms”, Robotics and Automation Magazine, pp.99-110, June, 2006.
[2] T. Bailey and H. Durrant-Whyte, “Simultaneous Localisation and Mapping (SLAM):Part II State of the Art”, Robotics and Automation Magazine, pp. 108-117,September, 2006.
[3] J.Civera, A.J .Davison, and J.M.M. Montiel, “Inverse Depth Parametrization for Monocular SLAM”,IEEE transactions on robotics, vol.24, No5, October 2008.
[4] J. M. M. Montiel, J. Civera, and A. J. Davison, “Unified Inverse Depth Parametrization for Monocular SLAM”, Robotics Science and Systems, RSS, Philadelphia, 2006.
[5] P. Gupta, N. da Vitoria Lobo and J. J. Laviola Jr, “Markerless tracking and gesture recognition using polar correlation of camera optical flow”, Machine Vision and Applications, 12 September 2012
[6] H .P. Morevec, “Towards automatic visual obstacle avoidance ”,
Proceedings of 5th International Joint Conference on Artificial Intelligence,pp.584,1977
[7] C. Harris and M. Stephens, “A combined corner and edge detector”, In Alvey Vision Conference, pp. 147-151, 1988.
[8] D. G. Lowe. “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[9] H. Bay, A. Ess, T. Tuytelaars and L. V. Gool, “SURF: Speeded-Up Robust Features”, Computer Vision and Image Understanding, vol.110, pp.346-359, 2008.
[10] R. G. Brown and P. Y. C. Hwang, “Introduction to Random Signals and Applied Kalman Filtering”, John Willey&Sons, 3rd Ed., 1997.
[11] G. Welch and G. Bishop, “An Introduction to the Kalman Filter”, UNC-Chapel Hill, TR 95-041, March 11, 2002.
[12] http://en.wikipedia.org/wiki/Hough_transform
[13] K. Mikolajczyk and C. Schmid, “Indexing based on scale invariant interest points”, International Conference on Computer Vision ,pp.525-531, 2001.
[14] T.Lindeberg, “Scale-space theory: A basic tool for analysing structures at different scales”, Journal of Applied Statistics, 21(2):224-270, 1994.
[15] J. J. Koenderink, “ The structure of images”, Biological Cybernetics,
50:363-396, 1984.
[16] M.Brown and D.G. Lowe. “Invariant features from interest point groups”, In British Machine Vision Conference, Cardiff, Wales, pp. 656-665, 2002.
[17] T. Lindeberg, “Feature Detection with Automatic Scale Selection”, International Journal of Computer Vision, 30: 79 - 116, 1998.
[18] L. Juan and O. Gwu, “A comparison of SIFT, PCA-SIFT and SURF”, Int. J. of Image Process, vol. 3, no. 4, pp. 143–152, Oct. 2009
[19]http://www.techbang.com/posts/11045-hard-to-see-google-street-view-fleet-fifth-generation-high-definition-street-view-images-on-location
[20] https://maps.google.com.tw/maps?hl=zh-TW
[21] https://developers.google.com/maps/documentation/streetview/
[22] http://mmdays.com/2007/05/16/knn/comment-page-1/
[23]http://ivyhere.pixnet.net/blog/post/49079774-%E7%AD%86%E8%A8%98-sift-%E5%B0%BA%E5%BA%A6%E4%B8%8D%E8%AE%8A%E7%89%B9%E5%BE%B5%E8%BD%89%E6%8F%9B
[24] 陳慶坤,步伐偵測與GPS整合之個人運動定位系統,國立台灣科 技大學機械工程研究所碩士論文,2011
[25] 李嘉欣,多視點輔助定位系統,國立台灣科技大學機械工程研究所碩士論文,2007
[26] 許竣揚,單一相機同時定位與環境地圖建製於二維移動載具之實 現,國立台灣科技大學機械工程研究所碩士論文,2011
[27] 林姿吟,基於立體視覺的3D影像定位,國立台灣科技大學機械工程研究所碩士論文,2011
[28] 劉家榮,以Android手機影像追蹤實現載具同時定位與建圖,國立台灣科技大學機械工程研究所碩士論文,2012