網路地圖的應用日新月異，自Google推出街景圖後，立基於街景圖的創意更是令人驚艷，其中不少是利用大量且連續地變換街景圖來創造視覺效果，我們因此發想一個應用使Google街景圖可以自動串接。
使用者在網頁上輸入一組有效起訖地址後，本系統可自動產生甲地到乙地的一段影片。系統流程分兩大部分，第一部分：透過Google API傳回兩地間之導航資訊，計算路程中會經過的GPS位置，並下載沿路的街景圖，此部分使用者可直接在瀏覽器上觀看街景的圖片轉換；第二部分：前步驟取得沿路的街景圖後，先偵測每張圖的道路消失點(Vanishing Point)，再利用消失點對齊圖片，最後將每張圖片串連成影片供使用者下載，本研究著重在都會市區的直線道路模擬，對於山區或鄉間彎曲道路的模擬則留至未來再討論。

Applications on electronic maps have made a major progress over the past few years. Since Google launched street view maps, many impressive creations based on street views have been brought to us. Many of them are using the idea of stringing up lots of street view to create special visual effects. We therefore want to create an application that can automatically string up Google street views.
When a user gives a start and end addresses on a web page, our system can automatically output a video which is generated from the Google street view images between the two locations. Our system can be divided into two parts. First, we retrieve the GPS locations where a street view exists on the path through Google API. Here, a user can see images being replaced repeatedly on a browser. Second, we download the images according to the GPS we obtained in the first part. After detecting the vanishing point of the road in every image, we use these vanishing points to align images. The aligned images will then be stringed up as a video for the user to download.
Our research focuses on animating straight roads often seen in metropolitan areas, as for winding-roads, they will be left for future work.

[1] D. Anguelov, C. Dulong and D. Filip. 2010. Google Street View: Capturing the World at Street Level, Computer, vol. 43 .
[2] A. Frome, G. Cheung and A. Abdulkader. 2009. Large-scale Privacy Protection in Google Street View(ICCV).
[3] J. Kopf, B. Chen, R. Szeliski and M. Cohen. 2010. Street Slide: Browsing Street Level Imagery. ACM SIGGRAPH.
[4] R. Toldo and A. Fusiello. 2008. Robust multiple structures estimation with J-Linkage. European Conference on Computer Vision(ECCV).
[5] J.-P. Tardif. 2009. Non-iterative Approach for Fast and Accurate Vanishing Point Detection, 12th IEEE International Conference on Computer Vision.
[6] R. G. von Gioi, J. Jakubowicz, J.-M. Morel and G. Randall. 2010. LSD: A Fast Line Segment Detector with a False Detection Control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 722.
[7] C. Feng, F. Deng, V. R. Kamat. 2010. Semi-automatic 3D Reconstruction of Piecewise Planar Building Models From Single Image. The 10th International Conference on Construction Applications of Virtual Reality.
[8] T. Gao and H. Aghajan. 2009. Lane Assignment Using Egocentric Smart Mobile Camera For Intelligent GPS Navigation. CVPR.
[9] D.H. Ballard. 1981. Generalizing the Hough Transform to Detect Arbitrary Shapes, Pattern Recognition, vol. 13, no. 2, pp. 111-122.
[10] P. Kahn, L. Kitchen and E.M. Riseman. 1990. A fast line finder for vision-guided robot navigation. IEEE Transactions on PAMI.
[11] L. Ballan, G. J. Brostow, J. Puwein and M. Pollefeys. 2010. Unstructured Video-Based rendering: Interactive Exploration of Casually Captured Videos. ACM SIGGRAPH.
[12] M. Goesele, J. Ackermann, S. Fuhrmann, C. Haubold and R. Klowsky. 2010. Ambient Point Clouds for View Interpolation. ACM Transactions on Graphics, Vol. 29, No. 4, Article 95
[13] J.B. Burns, A.R. Hanson and E.M. Riseman. 1986. Extracting Straight Lines, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 4, pp. 425-455.
[14] A. Desolneux, S. Ladjal, L. Moisan and J.M. Morel. 2002. Dequantizing Image Orientation. IEEE Trans. Image Processing, vol. 11, no. 10, pp. 1129-1140.
[15] LOWE, D. G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 2, 91–110.
[16] HARTLEY, R. I., AND ZISSERMAN, A.. 2000. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521623049.
[17] SNAVELY, N., SEITZ, S. M., AND SZELISKI, R. 2008. Skeletal graphs for efficient structure from motion. In Proc. CVPR.
[18] C. Rasmussen. 2004. Grouping Dominant Orientations for Ill-Structured Road Following. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
[19] GOESELE, M., SNAVELY, N., CURLESS, B., HOPPE, H., AND SEITZ, S. M. 2007. Multi-view stereo for community photo collections. In Proc. ICCV.
[20] J-C Bazin, Y. Seo, C. Demonceaux and P. Vasseur .2012. Globally Optimal Line Clustering and Vanishing Point Estimation in Manhattan World. CVPR.