Line Matching for Integration of Photographic and Geographic Databases

Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)


The aim of this chapter is to describe a new method for assigning a geographical position to an urban picture. The method is based only on the content of the picture. The photograph is compared to a sample of geolocated 3D images generated automatically from a virtual model of the terrain and the buildings. The relation between the picture and the images is built through the matching of detected lines in the photograph and in the image. The lines extraction is based on the Hough transform. This matching is followed by a statistical analysis to propose a probable location of the picture with an estimation of accuracy. The chapter presents and discusses the results of an experiment with data about Saint-Etienne, France and ends with proposals for improving and extending the method.


GIS Photo Matching lines Hough lines 3D reconstruction  Labels City 


  1. Cohen M, Toussaint G (1977) On the detection of structures in noisy pictures. Pattern Recogn 9:95–98CrossRefGoogle Scholar
  2. Crowley JL (2010) Détection et Description de Contraste. Unité de Formation et de Recherche en Informatique et Mathématiques Appliquées (UFR IMAG), de l’Université Joseph Fourier—Grenoble 1 (UJF), GrenobleGoogle Scholar
  3. Duda RO, Hart PE (1972) Use of the hough transformation to detect lines and curves in pictures. Commun ACM 15:11–15CrossRefGoogle Scholar
  4. Hays J, Efros AA (2008) IM2GPS: estimating geographic information from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2008, pp 1–8Google Scholar
  5. Hoiem D, Efros AA, Hebert M (2005) Geometric context from a single image. Proceedings of the 10th IEEE international conference on computer vision ICCV05, vol 1. IEEE Computer Society, pp 654–661Google Scholar
  6. Hoiem D, Efros AA, Hebert M (2007) Recovering surface layout from an image. Int J Comput Vis 75:151–172Google Scholar
  7. Hough PVC (1962) Method and means for recognizing complex patterns. US Patent, 3069654, 1962Google Scholar
  8. Kneepkens REJ (2005) Hough-based road detection. Technische Universiteit Eindhoven, PHD thesisGoogle Scholar
  9. Maitre H (1985) Un panorama de la transformation de hough. Traitement de Signal 2:305–317Google Scholar
  10. Moslah O (2011) Toward large scale urban environment Modeling from images. Dissertation, Cergy-PontoiseGoogle Scholar
  11. Rosenfeld A (1969) Picture processing by computer. Academic Press, New York and LondonGoogle Scholar
  12. Suh B, Bederson BB (2007) Semi-automatic photo annotation strategies using event-based clustering and clothing-based person recognition. Interact Comput 19:524–544. doi: 10.1016/j.intcom.2007.02.002 CrossRefGoogle Scholar
  13. Torniai C, Battle S, Cayzer S (2007) Sharing, discovering and browsing geotagged pictures on the web. Digital Media Systems Laboratory, HP Laboratories Bristol. Accessed on 15 June 2014
  14. Valentin R (2009) Reconnaissance de formes - Transformée de Hough. ENSEIRB-MATMECA à l’Institut Polytechnique de Bordeaux, BordeauxGoogle Scholar
  15. Yaegashi K, Yanai K (2009) Can geotags help image recognition? Advances in image and video technology. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 361–373Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.ISTHME-EVSJean Monnet University, CNRSF-Saint-Etienne Cedex 02France
  2. 2.ENISEF-Saint-Etienne Cedex 02France

Personalised recommendations