, Volume 13, Issue 2, pp 121–157 | Cite as

Automatic and Accurate Extraction of Road Intersections from Raster Maps

  • Yao-Yi ChiangEmail author
  • Craig A. Knoblock
  • Cyrus Shahabi
  • Ching-Chien Chen


Since maps are widely available for many areas around the globe, they provide a valuable resource to help understand other geospatial sources such as to identify roads or to annotate buildings in imagery. To utilize the maps for understanding other geospatial sources, one of the most valuable types of information we need from the map is the road network, because the roads are common features used across different geospatial data sets. Specifically, the set of road intersections of the map provides key information about the road network, which includes the location of the road junctions, the number of roads that meet at the intersections (i.e., connectivity), and the orientations of these roads. The set of road intersections helps to identify roads on imagery by serving as initial seed templates to locate road pixels. Moreover, a conflation system can use the road intersections as reference features (i.e., control point set) to align the map with other geospatial sources, such as aerial imagery or vector data. In this paper, we present a framework for automatically and accurately extracting road intersections from raster maps. Identifying the road intersections is difficult because raster maps typically contain much information such as roads, symbols, characters, or even contour lines. We combine a variety of image processing and graphics recognition methods to automatically separate roads from the raster map and then extract the road intersections. The extracted information includes a set of road intersection positions, the road connectivity, and road orientations. For the problem of road intersection extraction, our approach achieves over 95% precision (correctness) with over 75% recall (completeness) on average on a set of 70 raster maps from a variety of sources.


raster map road layer road intersection imagery conflation fusion vector data geospatial data integration 



This research is based upon work supported in part by the United States Air Force under contract number FA9550-08-C-0010, in part by the National Science Foundation under Award No. IIS-0324955, in part by the Air Force Office of Scientific Research under grant number FA9550-07-1-0416, in part by a gift from Microsoft, and in part by the Department of Homeland Security under ONR grant number N00014-07-1-0149. The U.S. Government is authorized to reproduce and distribute reports for Governmental purposes notwithstanding any copyright annotation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of any of the above organizations or any person connected with them. We would like to thank Dr. Chew Lim Tan for his generous sharing of their code in [6].


  1. 1.
    Agam G, Dinstein I (1996) Generalized morphological operators applied to map-analysis. In: The proceedings of the 6th international workshop on advances in structural and syntactical pattern recognition. Springer-Verlag, pp 60–69Google Scholar
  2. 2.
    Bixler JP (2000) Tracking text in mixed-mode documents. In: The ACM conference on document processing systems, ACM, Santa Fe, New Mexico, pp 177–185Google Scholar
  3. 3.
    Chen C-C, Knoblock CA, Shahabi C, Chiang Y-Y, Thakkar S (2004) Automatically and accurately conflating orthoimagery and street maps. In: The 12th ACM international symposium on advances in geographic information systems, ACM, Washington, D.C., pp 47–56Google Scholar
  4. 4.
    Chen C-C, Knoblock CA, Shahabi C (2006) Automatically conflating road vector data with orthoimagery. Geoinformatica 10(4):495–530CrossRefGoogle Scholar
  5. 5.
    Chen C-C, Knoblock CA, Shahabi C (2008) Automatically and accurately conflating raster maps with orthoimagery. GeoInformatica (in press)Google Scholar
  6. 6.
    Cao R, Tan CL (2001) Text/graphics separation in maps. In: The 4th international workshop on graphics recognition algorithms and applications, Kingston, Ontario. Springer Verlag, pp 167–177Google Scholar
  7. 7.
    Chiang Y-Y, Knoblock CA, Chen C-C (2005) Automatic extraction of road intersections from raster maps. In: The 13th ACM international symposium on advances in geographic information systems, Bremen, ACMGoogle Scholar
  8. 8.
    Chiang Y-Y, Knoblock CA (2006) Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines. In: The international conference on pattern recognition, Hong Kong, IEEE Computer SocietyGoogle Scholar
  9. 9.
    Desai S, Knoblock CA, Chiang Y-Y, Desai K, Chen C-C (2005) Automatically identifying and georeferencing street maps on the web. In: The 2nd international workshop on geographic information retrieval, Bremen, ACMGoogle Scholar
  10. 10.
    Fletcher LA, Kasturi R (1988) A robust algorithm for text string separation from mixed text/graphics images. IEEE Trans Pattern Anal Mach Intell 10(6):910–918CrossRefGoogle Scholar
  11. 11.
    Habib AF, Uebbing RE (1999) Automatic extraction of primitives for conflation of raster maps. Technical report. The Center for Mapping, The Ohio State UniversityGoogle Scholar
  12. 12.
    Heipk C, May H, Wiedemann C, Jamet O. (1997) Evaluation of automatic road extraction. In: The ISPRS Conference, vol 32, pp 3–2W3Google Scholar
  13. 13.
    Koutaki G, Uchimura K (2004) Automatic road extraction based on cross detection in suburb. In: Image processing: algorithms and systems III. Proceedings of the SPIE, vol 5299, pp 337–344Google Scholar
  14. 14.
    Keslassy I, Kalman M, Wang D, Girod B (2001) Classification of compound images based on transform coefficient likelihood. In: The international conference on image processing, Thessaloniki, IEEEGoogle Scholar
  15. 15.
    Li L, Nagy G, Samal A, Seth S, Xu Y (1999) Cooperative text and line-art extraction from a topographic map. In: Proceedings of the 5th international conference on document analysis and recognition, IEEEGoogle Scholar
  16. 16.
    Li L, Nagy G, Samal A, Seth S, Xu Y (2000) Integrated text and line-art extraction from a topographic map. IJDAR 2(4):177–185CrossRefGoogle Scholar
  17. 17.
    Myers GK, Mulgaonkar PG, Chen C-H, DeCurtins JL, Chen E (1996) Verification-based approach for automated text and feature extraction from raster-scanned maps. In: Lecture notes in computer science, vol 1072. Springer, pp 190–203Google Scholar
  18. 18.
    Nagy G, Sama A, Set S, Fisher T, Guthmann E, Kalafala K, Li L, Sivasubraniam S, Xu Y (1997) Reading street names from maps - Technical challenges. In: Procs. GIS/LIS conference, pp 89–97Google Scholar
  19. 19.
    Pratt WK (2001) Digital image processing: PIKS inside, 3rd edn. Wiley-Interscience, New YorkGoogle Scholar
  20. 20.
    Randen T, Husoy JH (1999) Filtering for texture classification: a comparative study. IEEE Trans Pattern Anal Mach Intell 21(4):291–310CrossRefGoogle Scholar
  21. 21.
    Samet H, Soffer A (1994) A legend-driven geographic symbol recognition system. In: The 12th international conference on pattern recognition, IEEE, Jerusalem, vol 2, pp 350–355, OctoberGoogle Scholar
  22. 22.
    Shi J, Tomasi C (1994) Good features to track. In: The IEEE conference on computer vision and pattern recognition, IEEE, SeattleGoogle Scholar
  23. 23.
    Sezgin M, Sankur B (2004) Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 13(1):146–165CrossRefGoogle Scholar
  24. 24.
    Salvatore S, Guitton P (2001) Contour line recognition from scanned topographic maps. Technical report. University of ErlangenGoogle Scholar
  25. 25.
    Tang YY, Lee S-W, Suen CY (1996) Automatic document processing: a survey. Pattern Recogn 29(12):1931–1952CrossRefGoogle Scholar
  26. 26.
    Velázquez A, Levachkine S (2003) Text/graphics separation and recognition in raster-scanned color cartographic maps. In: The 5th international workshop on graphics recognition algorithms and applications, Barcelona, CataloniaGoogle Scholar
  27. 27.
    Zack GW, Rogers WE, Latt SA (1977) Automatic measurement of sister chromatid exchange frequency. J Histochem Cytochem 25(7):741–753Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Yao-Yi Chiang
    • 1
    Email author
  • Craig A. Knoblock
    • 1
  • Cyrus Shahabi
    • 2
  • Ching-Chien Chen
    • 3
  1. 1.Department of Computer Science and Information Sciences InstituteUniversity of Southern CaliforniaMarina del ReyUSA
  2. 2.Computer Science DepartmentUniversity of Southern CaliforniaLos AngelesUSA
  3. 3.Geosemble TechnologiesEl SegundoUSA

Personalised recommendations