• DocumentCode
    1585668
  • Title

    Cadastre map assembling: a puzzle game resolution

  • Author

    Viglino, Jean-Marc ; Guigues, Laurent

  • Author_Institution
    Lab. MATIS, Inst. Geographique Nat., France
  • fYear
    2001
  • fDate
    6/23/1905 12:00:00 AM
  • Firstpage
    1235
  • Lastpage
    1239
  • Abstract
    The French cadastral map consists of over 500,000 map sheets that cover the whole territory. The raster digitisation of these paper maps is in progress. In order to exploit them, we have to assemble and geo-reference the set of maps to make them superimposable on other geographic information in a GIS. The problem can be seen as a complex jigsaw puzzle where the pieces are the cadastre sections extracted from the maps. In this paper, we present an automatic solution to this geographic jigsaw puzzle, based on a non-combinatorial optimisation method that maximises the "sticking" between every piece and its neighbours. The first step is to extract image features from the documents. Then we compute the sticking relationships between each pair of pieces. The puzzle resolution itself is based on an L1 norm optimisation. A method to detect process faults is discussed. The final goal of the process is to integrate every piece of the puzzle (i.e. the cadastre maps) into a national geographic reference frame and database
  • Keywords
    cartography; computational geometry; document image processing; feature extraction; geographic information systems; optimisation; French cadastral map; L1 norm optimisation; cadastre map assembly; document analysis; document database; extracted cadastre sections; geographic database; geographic information system; geographic jigsaw puzzle; georeferencing; image feature extraction; national geographic reference frame; noncombinatorial optimisation method; paper map sheets; process fault detection; puzzle game resolution; raster digitisation; sticking relationships; superimposable maps; Assembly; Data mining; Fault detection; Feature extraction; Geographic Information Systems; Image databases; Optimization methods; Roads; Spatial databases; Text analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
  • Conference_Location
    Seattle, WA
  • Print_ISBN
    0-7695-1263-1
  • Type

    conf

  • DOI
    10.1109/ICDAR.2001.953979
  • Filename
    953979