Improving Pixel-based VHR Land-cover Classifications of Urban Areas with Post-classification Techniques

In this paper, 3 post-classification techniques are proposed to improve the information content, thematic accuracy, and spatial structure of pixel-based classifications of complex urban areas. A shadow-removal technique based on a neural network that was trained using the output of a soft classification is proposed to assign shadow pixels to meaningful land-cover classes. Knowledge-based rules are suggested to correct wrongly classified pixels and to improve the overall accuracy of the land-cover map. Lastly, a region-based filter is applied to reduce high-frequency structural clutter. The 3 techniques were successfully applied to a pixel-based classification of a QuickBird image covering the city of Ghent, Belgium, improving the kappa index-of-agreement from 0.82 to 0.86, and transforming the shadow pixels into meaningful land-cover information.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00991112
• Authors:
  • Van de Voorde, Tim
  • De Genst, William
  • Canters, Frank
• Publication Date: 2007-9

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 1017-1027
• Serial:
  • Photogrammetric Engineering and Remote Sensing
  • Volume: 73
  • Issue Number: 9
  • Publisher: American Society for Photogrammetry and Remote Sensing
  • ISSN: 0099-1112

Subject/Index Terms

• TRT Terms: Digital mapping; Landsat satellites; Neural networks; Photogrammetry; Spatial analysis; Urban areas
• Subject Areas: Design; Highways; I20: Design and Planning of Transport Infrastructure;

Filing Info

• Accession Number: 01076835
• Record Type: Publication
• Files: TRIS
• Created Date: Sep 24 2007 9:14AM