Advertisement

Generating Named Road Vector Data from Raster Maps

  • Yao-Yi Chiang
  • Craig A. Knoblock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7478)

Abstract

Raster maps contain rich road information, such as the topology and names of roads, but this information is “locked” in images and inaccessible in a geographic information system (GIS). Previous approaches for road extraction from raster maps typically handle this problem as raster-to-vector conversion and hence the extracted road vector data are line segments without the knowledge of road names and where a road starts and ends. This paper presents a technique that builds on the results from our previous road vectorization and text recognition work to generate named road vector data from raster maps. This technique first segments road vectorization results using road intersections to determine the lines that represent individual roads in the map. Then the technique exploits spatial relationships between roads and recognized text labels to generate road names for individual road segments. We implemented this approach in our map processing system, called Strabo, and demonstrate that the system generates accurate named road vector data on example maps with 92.83% accuracy.

Keywords

Raster map road vectorization text recognition named road vector data map labeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agarwal, P.K., van Kreveld, M., Suri, S.: Label placement by maximum independent set in rectangles. Computational Geometry 11(3-4), 209–218 (1998)MathSciNetzbMATHCrossRefGoogle Scholar
  2. Bin, D., Cheong, W.K.: A system for automatic extraction of road network from maps. In: Proceedings of the IEEE International Joint Symposia on Intelligence and Systems, pp. 359–366 (1998)Google Scholar
  3. Chiang, Y.-Y.: Harvesting Geographic Features from Heterogeneous Raster Maps. PhD thesis, University of Southern California (2010)Google Scholar
  4. Chiang, Y.-Y., Knoblock, C.A.: A general approach for extracting road vector data from raster maps. International Journal on Document Analysis and Recognition (2011a), doi: 10.1007/s10032-011-0177-1Google Scholar
  5. Chiang, Y.-Y., Knoblock, C.A.: Recognition of multi-oriented, multi-sized, and curved text. In: Proceedings of the Eleventh International Conference on Document Analysis and Recognition (2011b)Google Scholar
  6. Doddi, S., Marathe, M.V., Mirzaian, A., Moret, B.M.E., Zhu, B.: Map labeling and its generalizations. In: Proceedings of the Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 148–157 (1997)Google Scholar
  7. Edmondson, S., Christensen, J., Marks, J., Shieber, S.M.: A general cartographic labelling algorithm. Cartographica: The International Journal for Geographic Information and Geovisualization 33(4), 13–24 (1996)CrossRefGoogle Scholar
  8. Freeman, H.: Automated cartographic text placement. Pattern Recognition Letters 26, 287–297 (2005)CrossRefGoogle Scholar
  9. Goldberg, D.W., Wilson, J.P., Knoblock, C.A.: Extracting geographic features from the internet to automatically build detailed regional gazetteers. International Journal of Geographic Information Science 23(1), 92–128 (2009)CrossRefGoogle Scholar
  10. Itonaga, W., Matsuda, I., Yoneyama, N., Ito, S.: Automatic extraction of road networks from map images. Electronics and Communications in Japan (Part II: Electronics) 86(4), 62–72 (2003)CrossRefGoogle Scholar
  11. MapScan: MapScan for Windows Software Package for Automatic Map Data Entry, User’s Guide and Reference Manual. Computer Software and Support for Population Activities, INT/96/P74, United Nations Statistics Division, New York, NY 10017, USA (1998)Google Scholar
  12. Pouderoux, J., Gonzato, J.C., Pereira, A., Guitton, P.: Toponym recognition in scanned color topographic maps. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, vol. 1, pp. 531–535 (2007)Google Scholar
  13. Roy, P.P., Pal, U., Llados, J., Kimura, F.: Multi-oriented English text line extraction using background and foreground information. In: IAPR International Workshop on Document Analysis Systems, pp. 315–322 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yao-Yi Chiang
    • 1
  • Craig A. Knoblock
    • 2
  1. 1.Information Sciences Institute and Spatial Sciences InstituteUniversity of Southern CaliforniaMarina del ReyUSA
  2. 2.Department of Computer Science and Information Sciences InstituteUniversity of Southern CaliforniaMarina del ReyUSA

Personalised recommendations