臺灣因地質破碎，構造活動頻繁，並經常受颱風，地震等天災影響，造成山坡地極不穩定，公路邊坡災害層出不窮，危害國家經濟與交通命脈甚鉅。一般巡路工作多以人工步行配合目視方法檢查道路與邊坡現況，不僅耗時費力，更欠缺與過去資料客觀比對之科學根據，不易掌握公路邊坡災害細微而漸進之發生前兆。多期環景攝影可以低成本快速獲取監控路段多視角與高解析度之影像，若能結合影像變異分析技術，快速自動篩選地貌改變而有災害發生潛勢之路段，進一步深入調查，可防微杜漸，對公路邊坡安全提出更加完善之養護建議。
　　本研究藉由車載之環景攝影機通過影像匹配技術管理公路安全以及評估，於台中中橫公路台八線及台八甲線共13公里長之路段進行環景攝影，經比對兩期資料後選取12處變異顯著之地區，將環景攝影之深入分析面裁切進行分析，首先由使用影像匹配技術定尺度特徵轉換方法(Scale Invariant Feature Transform, SIFT)萃取作為準則特徵點，接著使用交互相關方法(Cross Correlation)、相位相關方法（Phase Correlation）由準則特徵點選兩期影像間相關點，由三種幾何配準方法兩期影像中萃取理想特徵點，由此特徵點比較前後期影像之相關性，並且分析影像雜訊、旋轉及角度變化與對比變化，此外根據特徵點對兩期裁切影像進行點點配準，以準確地圈繪出變異區域以及公路邊坡崩塌面積變化；最後結合運動回復結構(Structure from Motion, SfM)和多視影像立體(Multi-View Stereo, MVS)的方法，接著利用三維場景構造技術，還原公路邊坡之三維立體空間資訊，以及數值地表模型(DSM)的建製。結果顯示本研究所使用之變異分析技術可以快速而有效地處理多期環景攝影資料，提供公路邊坡安全評估所需之變異區域關鍵資訊。

The broken terrain and frequent earthquakes, together with the heavy precipitation during the rainy and typhoon seasons, pose a grave threat toslope stability in Taiwan. As a result, slope disasters are frequently found along the highways in mountainous area and seriously endanger Taiwan’s lifeline of transportation and economy. The traditional approach for highway maintenance relies on patrolmento visually screening the slopes from the ground or the patrol vehicle. Such an approach, however, requires considerable manpower and time, yet provides very limited information on spatial coverage. Lacking of an objective and quantitative comparison between the latest observations to the historical one, there is no way to diagnose the subtle yet progressive signs of slope disasters. This research employs two panorama videos of New Central Cross-Island Highway, taken on 20 April 2011 and 22 November 2011, respectively. A total of 12 sites with high risk of slope disasters are identified and selected. The multi-temporal panoramas of each site are extracted from the videos for change detection. Since the accurate GPS and IMU data were not recorded in an ordinary petrol vehicle, and these two videos were not taken from the same viewing angles along the same route, we integrate three approaches to coregister the multi-temporal panoramas. First, the adaptive enhancement is applied to the multi-temporal panoramas and scale invariant feature transform (SIFT) approach is used to generate a set of key points. These key points are examined by both the cross-correlation (CC) approach and the phase-correlation (PC) approach, with the intention to fill out those problematic points. Based on these robust key points, the PC approach is used again to generate a large number of tie points and each point is double checked with CC approach. With the large amount of accurate tie points, the multi-temporal panoramas can be accurately coregistered to meet the requirements of change detection. The results demonstrate that the difference between the coregistered multi-temporal panoramas provides reliable and quantitative information of subtle changes on highway slopes. IIn addition, combining Application of SfM (Structure from Motion) and MSV (Multi-view Stereo) method to generate 3D Scene Reconstruction builds slope information of road in 3D space and establish DSM. This study expresses application of the analyzing variance techniques can carry out and handle multi-panorama information quickly and efficiently. This is a low-cost approach to assess the safety of the highway slopes.

ISTI-CNR(2012), MeshLab, http://meshlab.sourceforge.net/.
Agarwal, S., Y. Furukawa, N. Snavely, B. Curless, S. M. Seitz, and R. Szeliski (2010), Reconstructing rome, Computer, 43(6), 40-47.
Akca, D. (2013), Photogrammetric Monitoring of an Artificially Generated Shallow Landslide, Photogrammetric Record, 28(142), 178-195.
Ayache, N., and F. Lustman (1991), Trinocular stereovision for robotics, Ieee Transactions on Pattern Analysis and Machine Intelligence, 13(1).
Ayalew, L., and H. Yamagishi (2005), The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan, Geomorphology, 65(1), 15-31.
Bay, H., A. Ess, T. Tuytelaars, and L. Van Gool (2008), Speeded-up robust features (SURF), Computer Vision and Image Understanding, 110(3), 346-359.
Cao, Y., and L. Yan (2012), Automatic road network extraction from UAV image in mountain area, paper presented at Image and Signal Processing (CISP), 2012 5th International Congress on, IEEE.
Castilla, G., R. H. Guthrie, and G. J. Hay (2009), The land-cover change mapper (LCM) and its application to timber harvest monitoring in Western Canada, Photogrammetric engineering and remote sensing, 75(8), 941-950.
Cignoni, P., M. Corsini, and G. Ranzuglia (2008), Meshlab: an open-source 3D mesh processing system, Ercim news, 73, 45-46.
Corominas, J., R. Copons, J. M. Vilaplana, J. Altimir, and J. Amigó (2003), Shallow Integrated landslide susceptibility analysis and hazard assessment in the Principality of Andorra, Natural Hazards, 30(3), 421-435.
Dahal, R. K., S. Hasegawa, A. Nonomura, M. Yamanaka, S. Dhakal, and P. Paudyal (2008), Predictive modelling of rainfall-induced landslide hazard in the Lesser Himalaya of Nepal based on weights-of-evidence, Geomorphology, 102(3), 496-510.
Enami, N., N. Ukita, and M. Kidode (2009), IMAGE MATCHING WITH A CAR-MOUNTED CAMERA ROBUST TO CHANGES IN IMAGING CONDITIONS, International Journal of Pattern Recognition and Artificial Intelligence, 23(7), 1369-1395.
Fischler, M. A., and R. C. Bolles (1981), Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 24(6), 381-395.
Fujisawa, K., G. Marcato, Y. Nomura, and A. Pasuto (2010), Management of a typhoon-induced landslide in Otomura (Japan), Geomorphology, 124(3), 150-156.
Furukawa, Y. (2010a), Clustering Views for Multi-view Stereo (CMVS), edited.
Furukawa, Y. (2010b), Phatch-based Multi-view Stereo Software (PMVS-Version2), http://www.di.ens.fr/pmvs/.
Furukawa, Y. (2011), Multi-View Reconstruction Techniques in Computer Vision, International Journal of Computer Vision.
Furukawa, Y., and J. Ponce (2007), Accurate, dense, and robust multi-view stereopsis, paper presented at Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on, IEEE.
Furukawa, Y., and J. Ponce (2010), Accurate, dense, and robust multiview stereopsis, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(8), 1362-1376.
Harris, C., and M. Stephens (1988), A combined corner and edge detector, Manchester, UK.
Jacosek, M. (2012), CMPMVS 0.6.0, edited.
Jancosek, M., and T. Pajdla (2011), Multi-view reconstruction preserving weakly-supported surfaces, IEEE.
Jebara, T., A. Azarbayejani, and A. Pentland (1999), 3D structure from 2D motion, Signal Processing Magazine, IEEE, 16(3), 66-84.
Ke, Y., and R. Sukthankar (2004), PCA-SIFT: A more distinctive representation for local image descriptors, paper presented at Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, IEEE.
Kuglin, C. (1975), The Phase Correlation Image Alignment Methed, paper presented at Proc. Int. Conference Cybernetics Society.
Lato, M., J. Hutchinson, M. Diederichs, D. Ball, and R. Harrap (2009), Engineering monitoring of rockfall hazards along transportation corridors: using mobile terrestrial LiDAR, Nat. Hazards Earth Syst. Sci, 9(3), 935-946.
Lato, M. J., M. S. Diederichs, D. J. Hutchinson, and R. Harrap (2012), Evaluating roadside rockmasses for rockfall hazards using LiDAR data: optimizing data collection and processing protocols, Natural Hazards, 60(3), 831-864.
Lewis, J. (1995), Fast template matching, paper presented at Vision Interface.
Lhuillier, M., and L. Quan (2005), A quasi-dense approach to surface reconstruction from uncalibrated images, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27(3), 418-433.
Lindeberg, T. (1994), Scale-space theory: A basic tool for analyzing structures at different scales, Journal of applied statistics, 21(1-2), 225-270.
Lindeberg, T. (1998), Edge detection and ridge detection with automatic scale selection, International Journal of Computer Vision, 30(2), 117-156.
Liu, C. C. (2006), Processing of FORMOSAT-2 daily revisit imagery for site surveillance, Geoscience and Remote Sensing, IEEE Transactions on, 44(11), 3206-3214.
Liu, C. C., Y. Y. Chen, and C. W. Chen (2013), Application of multi-scale remote sensing imagery to detection and hazard analysis, Natural Hazards, 65(3), 2241-2252.
Liu, C. C., C. L. Shieh, C. A. Wu, and M. L. Shieh (2009), Change detection of gravel mining on riverbeds from the multi‐temporal and high‐spatial‐resolution formosat‐2 imagery, River Research and Applications, 25(9), 1136-1152.
Liu, C. C., J. G. Liu, C. W. Lin, A. M. Wu, S. H. Liu, and C. L. Shieh (2007), Image processing of FORMOSAT‐2 data for monitoring the South Asia tsunami, International Journal of Remote Sensing, 28(13-14), 3093-3111.
Lowe, D. G. (1999), Object recognition from local scale-invariant features, Ieee.
Nagai, M., T. Chen, R. Shibasaki, H. Kumagai, and A. Ahmed (2009), UAV-Borne 3-D Mapping System by Multisensor Integration, Ieee Transactions on Geoscience and Remote Sensing, 47(3), 701-708.
Niethammer, U., M. R. James, S. Rothmund, J. Travelletti, and M. Joswig (2012), UAV-based remote sensing of the Super-Sauze landslide: Evaluation and results, Engineering Geology, 128, 2-11.
Nieweglowski, J., T. G. Campbell, and P. Haavisto (1993), A novel video coding scheme based on temporal prediction using digital image warping, Consumer Electronics, IEEE Transactions on, 39(3), 141-150.
Nishimura, S. e. a. (2011), The Measurement and Monitoring at Gunkanjima-Island by Using 3D laser scanner and Sphere Camera (in japanese), Proceedings of JSEM Annual Conference on Experimental Mechanics(163-168).
Research, P. G. (2008), “Overview of the Ladybug image stitching process” Technical Application Note TAN2008010.
Rusu, R. B., and S. Cousins (2011), 3d is here: Point cloud library (pcl), paper presented at Robotics and Automation (ICRA), 2011 IEEE International Conference on, IEEE.
Schmid, C., and R. Mohr (1997), Local grayvalue invariants for image retrieval, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(5), 530-535.
Seitz, S. M., B. Curless, J. Diebel, D. Scharstein, and R. Szeliski (2006), A comparison and evaluation of multi-view stereo reconstruction algorithms, paper presented at Computer vision and pattern recognition, 2006 IEEE Computer Society Conference on, IEEE.
Shimizu, M., and M. Okutomi (2005), Sub-pixel estimation error cancellation on area-based matching, International Journal of Computer Vision, 63(3), 207-224.
Snavely, N. (2010), Bundler, http://www.cs.cornell.edu/~snavely/bundler/.
Snavely, N., S. M. Seitz, and R. Szeliski (2008), Modeling the world from internet photo collections, International Journal of Computer Vision, 80(2), 189-210.
Szeliski, R. (2011), Computer vision: algorithms and applications, Springer.
Takita, K., M. A. MUQUIT, and T. HIGUCHI (2004), A sub-pixel correspondence search technique for computer vision applications, IEICE transactions on fundamentals of electronics, communications and computer sciences, 87(8), 1913-1923.
Tao, C. V. (2000), Mobile mapping technology for road network data acquisition, Journal of Geospatial Engineering, 2(2), 1-14.
Travelletti, J., C. Delacourt, P. Allemand, J. P. Malet, J. Schmittbuhl, R. Toussaint, and M. Bastard (2012), Correlation of multi-temporal ground-based optical images for landslide monitoring: Application, potential and limitations, ISPRS Journal of Photogrammetry and Remote Sensing, 70, 39-55.
Triggs, B., P. F. McLauchlan, R. I. Hartley, and A. W. Fitzgibbon (2000), Bundle adjustment—a modern synthesis, in Vision algorithms: theory and practice, edited, pp. 298-372, Springer.
Tsutsui, K., S. Rokugawa, H. Nakagawa, S. Miyazaki, C.-T. Cheng, T. Shiraishi, and S.-D. Yang (2007), Detection and volume estimation of large-scale landslides based on elevation-change analysis using DEMs extracted from high-resolution satellite stereo imagery, Geoscience and Remote Sensing, IEEE Transactions on, 45(6), 1681-1696.
Turner, A. K., J. Kemeny, S. Slob, and R. Hack (2006), Evaluation, and management of unstable rock slopes by 3-D laser scanning, International association for engineering geology and the environment. The Geological Society of London, 1-11.
Viola, P., and M. J. Jones (2004), Robust real-time face detection, International Journal of Computer Vision, 57(2), 137-154.
Wood, G. A., and R. N. Marshall (1986), The accuracy of DLT extrapolation in three-dimensional film analysis, Journal of Biomechanics, 19(9), 781-785.
Wu, C. (2011), Visual SFM. , http://homes.cs.washington.edu/~ccwu/vsfm/
Wu, C. (2013), Towards Linear-time Incremental Structure from Motion.
Yoo, J. C., and T. H. Han (2009), Fast normalized cross-correlation, Circuits, Systems, and Signal Processing, 28(6), 819-843.
Zhang, Z. (2000), A flexible new technique for camera calibration, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(11), 1330-1334.
本道貴行, and 黄瀬浩一 (2008), 大規模画像認識のための局所特徴量の性能比較, 画像と認識・理解シンポジウム (MIRU2008) 論文集, 580-587.
交通部公路總局 (2010), 莫拉克風災槍救與復建實錄.
楊善智 (2008), 數值高程模型之品質評估, Jourmal of Photogrammetry and Remote Sensing, Volume 13, No.3, Sepetmber 2008, pp.195-206
萬獻銘 (1987), 中橫公路邊坡崩塌地黏土礦物與坡面破壞之關係研究.