中央研究院人文社會科學研究中心保存數量龐大的台灣早期空照底片與相片，並且透過數位典藏計劃對其進行全面數位化的掃描作業，其中有部分歷史航照擁有內、外方位資訊，比較容易透過人工進行地理對位。另外有很大部分的航照沒有相關的方位資訊，本研究使用電腦圖學發展自動化流程，利用SIFT影像匹配演算法(Scale Invariant Feature Transform)與RANSAC除錯理論(RANdom SAmple Consensus)自動尋找歷史航照之間的匹配點，並參考相鄰矩陣(Adjacency matrix)的概念儲存影像匹配之成果，自動建立連結點與多重點的關係。本研究在近代的衛星影像上尋找歷史航照所對應的控制點，即可利用網型平差計算座標轉換參數，將歷史航照轉換至地面座標系統。由於大部分的歷史航照所拍攝區域為台灣的平坦地區，本研究使用二維仿射轉換和二維投影轉換作為平差計算的數學模型，並在福衛二號衛星影像上尋找對應的地面控制點，進行座標轉換參數的計算。最後以兩種轉換參數將歷史航照影像再取樣，並且完成地理對位，最後歷史航照能與其它具有地理對位資訊的影像共同展示在相同的座標系統。由於航照影像能提供拍攝當時最直接的地表資訊，大量歷史航照經由高度自動化的處理，對於地理時空資訊相關研究有所助益，例如我們可以利用多時期的航空影像來分析不同年代的地表變遷、都市開發、海岸線監測等探討。

Aerial photographs directly show the reality of geographical environment, and historical ones provide the spatial information in the past. The Research Center for Humanities and Social Sciences (RCHSS) of Taiwan Academia Sinica, has conserved and scanned abundant historical aerial photographs. Most of them haven’t been georeferenced since there was no precise POS system for orientation assisting in the past. With digitized historical aerial photographs, we can handle the great quantity of images by using computer vision techniques. By applying SIFT image matching method, we develop an automatic process to match historical aerial photographs with higher precision and efficiency of image matching. And we use the concept of adjacency matrix for recording the result of image matching. Add control point measurements for calculating parameters of coordinate transformation through least square adjustment is the only manual procedure. The developed method allows us to georeference hundreds of historical aerial photographs automatically. Therefore, temporal environmental changes can be investigated with those geo-referenced temporal spatial data.

江若慈. (2014). 以時空資訊探討百年來台南古都沿海地區的土地利用變遷. 成功大學測量及空間資訊學系學位論文, pp.1~77.

張莉雪, 陳伯傳, 周士傑, & 陳乃宇. (2014). 福衛二號排程與災防雲端應用服務. 航測及遙測學刊, 18(1), pp.13~27.

梁平, 莊永忠, 吳治達, 詹進發, & 廖泫銘. (2011). 多源遙測影像於宜蘭海岸濱線變遷偵測之應用. 地理研究, (55), pp.47~68.

莊育侃. (2010). 運用歷史航照與日治地形圖資料探討花蓮地區之地形變遷. 臺北科技大學土木與防災研究所學位論文, pp.1~133.

饒芳如. (2014). 歷史 GIS 資料處理-結合 SIFT 與最小二乘法於歷史航照影像自動對位. 成功大學測量及空間資訊學系學位論文, pp.1~72.

Adami, A. (2015). 4D City transformations by time series of aerial photographs. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(5), pp.339~344.

Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Computer vision and image understanding, 110(3), pp.346~359.

Belcher, C., & Du, Y. (2009). Region-based SIFT approach to iris recognition. Optics and Lasers in Engineering, 47(1), pp.139~147.

Brown, M., & Lowe, D. G. (2007). Automatic panoramic image stitching using invariant features. International Journal of Computer Vision, 74(1), pp.59~73.

Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), pp.381~395.

Gong, M., Zhao, S., Jiao, L., Tian, D., & Wang, S. (2014). A novel coarse-to-fine scheme for automatic image registration based on SIFT and mutual information. IEEE Transactions on Geoscience and Remote Sensing, 52(7), pp.4328~4338.

Harris, C., & Stephens, M. (1988). A combined corner and edge detector. Proceedings of the 4th Alvey Vision Conference, pp.147~151.

Juan, L., & Gwun, O. (2009). A comparison of sift, pca-sift and surf. International Journal of Image Processing (IJIP), 3(4), pp.143~152.

Kadmon, R., & Harari-Kremer, R. (1999). Studying long-term vegetation dynamics using digital processing of historical aerial photographs. Remote Sensing of Environment, 68(2), pp.164~176.

Kim, J. S., Miller, C. C., & Bethel, J. (2010). Automated Georeferencing of Historic Aerial Photography. Journal of Terrestrial Observation, 2(1), pp.6.

Lowe, D. G. (1999). Object recognition from local scale-invariant features. Proceednig of International Conference on Computer Vision, pp.1150~1157.

Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), pp.91~110.

Mikolajczyk, K., & Schmid, C. (2004). Scale & affine invariant interest point detectors. International Journal of Computer Vision, 60(1), pp.63~86.

Moravec, H. P. (1980). Obstacle avoidance and navigation in the real world by a seeing robot rover. STANFORD UNIV CA DEPT OF COMPUTER SCIENCE, No. STAN-CS-80-813.

Munich, M. E., Pirjanian, P., Di Bernardo, E., Goncalves, L., Karlsson, N., & Lowe, D. (2006). SIFT-ing through features with ViPR. Ieee Robotics & Automation Magazine, 13(3), pp.72~77.

Nebiker, S., Lack, N., & Deuber, M. (2014). Building change detection from historical aerial photographs using dense image matching and object-based image analysis. Remote Sensing, 6(9), pp.8310~8336.

Rosten, E., & Drummond, T. (2006). Machine learning for high-speed corner detection. Proceednig of European conference on computer vision, pp.430~443.

Yu, L., Zhang, D., & Holden, E.-J. (2008). A fast and fully automatic registration approach based on point features for multi-source remote-sensing images. Computers & Geosciences, 34(7), pp.838~848.