Share Email Print
cover

Proceedings Paper

Automatic knowledge-based extraction of real-world objects from scanned maps
Author(s): Helmut Mayer
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For the automation of this task a new approach based on a multi-level model is presented. It is not restricted to the recognition of graphics but also uses knowledge about the topographic objects of the real world depicted in the map like roads, buildings, etc. in the form of their properties and relations. The model is represented by means of semantic networks and frames. It is utilized data- as well as model-driven. The approach has been tested on sections of Bavarian cadastral maps 1:1000 and 1:5000. Roads constituting the road network, pavements and roadsides were recognized in both maps. Additionally all buildings and the gardens were recognized in the map 1:1000 and meadows and fields were distinguished in the map 1:5000. The results show the applicability of the approach for automatic map interpretation.

Paper Details

Date Published: 17 August 1994
PDF: 8 pages
Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182869
Show Author Affiliations
Helmut Mayer, Technical Univ. Munich (Germany)


Published in SPIE Proceedings Vol. 2357:
ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision
Heinrich Ebner; Christian Heipke; Konrad Eder, Editor(s)

© SPIE. Terms of Use
Back to Top