Advertisement

A Hough Voting Strategy for Registering Historical Aerial Images to Present-Day Satellite Imagery

  • Sebastian Zambanini
  • Robert Sablatnig
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10484)

Abstract

In this paper we present an approach for the georeferencing of historical World War II images by registering the images to present-day satellite imagery, with the aim of supporting the risk assessment of unexploded ordnances. We propose to exploit the local geometry of corresponding interest points in a Hough voting scheme to identify the most likely transformation parameters between the images. Our method combines the evidences from local as well as global correspondences and uses a spatial zoning rule to establish solutions with preferably uniformly distributed correspondences. An experimental evaluation is conducted on a set of 42 pairs of historical and present-day images and reveals the outstanding performance of our method compared to state-of-the-art image matching and registration algorithms, including commonly used hypothesize-and-verify and graph matching methods.

Keywords

Historical image registration Georeferencing Hough voting 

Notes

Acknowledgements

This work is supported by the Austrian Research Promotion Agency (FFG) under project grant 850695. The authors wish to thank Luftbilddatenbank Dr. Carls GmbH.

Acquisition of historical aerial imagery: Luftbilddatenbank Dr. Carls GmbH; Sources of historical aerial imagery: National Archives and Records Administration (Washington, D.C.) and Historic Environment Scotland (Edinburgh).

References

  1. 1.
    Abrate, M., Bacciu, C., Hast, A., Marchetti, A., Minutoli, S., Tesconi, M.: Geomemories a platform for visualizing historical, environmental and geospatial changes in the italian landscape. ISPRS Int. J. Geo-Inf. 2(2), 432–455 (2013)CrossRefGoogle Scholar
  2. 2.
    Bouchiha, R., Besbes, K.: Comparison of local descriptors for automatic remote sensing image registration. Sig. Image Video Process. 9(2), 463–469 (2015)CrossRefGoogle Scholar
  3. 3.
    Bowen, F., Hu, J., Du, E.Y.: A multistage approach for image registration. IEEE Trans. Cybern. 46(9), 2119–2131 (2016)CrossRefGoogle Scholar
  4. 4.
    Busé, M.S.: WWII ordnance still haunts europe and the asia-pacific rim. J. Conv. Weapons Destr. 4(2), 83–87 (2016)Google Scholar
  5. 5.
    Chen, H.Y., Lin, Y.Y., Chen, B.Y.: Co-segmentation guided hough transform for robust feature matching. IEEE PAMI 37(12), 2388–2401 (2015)CrossRefGoogle Scholar
  6. 6.
    Cho, M., Lee, K.M.: Progressive graph matching: making a move of graphs via probabilistic voting. In: CVPR, pp. 398–405 (2012)Google Scholar
  7. 7.
    Cléry, I., Pierrot-Deseilligny, M., Vallet, B.: Automatic georeferencing of a heritage of old analog aerial photographs. ISPRS Ann. 2(3), 33–40 (2014)Google Scholar
  8. 8.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Gong, M., Zhao, S., Jiao, L., Tian, D., Wang, S.: A novel coarse-to-fine scheme for automatic image registration based on sift and mutual information. IEEE GRS 52(7), 4328–4338 (2014)Google Scholar
  10. 10.
    Jao, F.J., Chu, H.J., Tseng, Y.H.: Historical image registration and land-use land-cover change analysis. Environments 1(2), 181–189 (2014)CrossRefGoogle Scholar
  11. 11.
    Jégou, H., Douze, M., Schmid, C.: Improving bag-of-features for large scale image search. IJCV 87(3), 316–336 (2010)CrossRefGoogle Scholar
  12. 12.
    Le Moigne, J., Netanyahu, N.S., Eastman, R.D.: Image Registration for Remote Sensing. Cambridge University Press, Cambridge (2011)CrossRefzbMATHGoogle Scholar
  13. 13.
    Liang, J., Liu, X., Huang, K., Li, X., Wang, D., Wang, X.: Automatic registration of multisensor images using an integrated spatial and mutual information (SMI) metric. IEEE GRS 52(1), 603–615 (2014)Google Scholar
  14. 14.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  15. 15.
    Ma, J., Zhou, H., Zhao, J., Gao, Y., Jiang, J., Tian, J.: Robust feature matching for remote sensing image registration via locally linear transforming. IEEE GRS 53(12), 6469–6481 (2015)Google Scholar
  16. 16.
    Ma, W., Wen, Z., Wu, Y., Jiao, L., Gong, M., Zheng, Y., Liu, L.: Remote sensing image registration with modified sift and enhanced feature matching. IEEE GRSL 14(1), 3–7 (2017)Google Scholar
  17. 17.
    Merler, S., Furlanello, C., Jurman, G.: Machine learning on historic air photographs for mapping risk of unexploded bombs. In: Roli, F., Vitulano, S. (eds.) ICIAP 2005. LNCS, vol. 3617, pp. 735–742. Springer, Heidelberg (2005). doi: 10.1007/11553595_90 CrossRefGoogle Scholar
  18. 18.
    Murino, V., Castellani, U., Etrari, A., Fusiello, A.: Registration of very time-distant aerial images. In: ICIP, vol. 3, pp. 989–992. IEEE (2002)Google Scholar
  19. 19.
    Nagarajan, S., Schenk, T.: Feature-based registration of historical aerial images by area minimization. ISPRS J. Photogramm. Remote Sens. 116, 15–23 (2016)CrossRefGoogle Scholar
  20. 20.
    Paunila, S.: Managing residual clearance: learning from Europe’s past. J. Conv. Weapons Destr. 18(1), 22–25 (2015)Google Scholar
  21. 21.
    Raguram, R., Frahm, J.M., Pollefeys, M.: A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 500–513. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-88688-4_37 CrossRefGoogle Scholar
  22. 22.
    Sanromà, G., Alquézar, R., Serratosa, F.: A new graph matching method for point-set correspondence using the EM algorithm and softassign. CVIU 116(2), 292–304 (2012)Google Scholar
  23. 23.
    Vakalopoulou, M., Karantzalos, K., Komodakis, N., Paragios, N.: Simultaneous registration and change detection in multitemporal, very high resolution remote sensing data. In: CVPR Workshops, pp. 61–69 (2015)Google Scholar
  24. 24.
    Wen, G.J., Lv, J.J., Yu, W.X.: A high-performance feature-matching method for image registration by combining spatial and similarity information. IEEE GRS 46(4), 1266–1277 (2008)Google Scholar
  25. 25.
    Zitova, B., Flusser, J.: Image registration methods: a survey. IVC 21(11), 977–1000 (2003)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Computer Vision LabTU WienViennaAustria

Personalised recommendations