Advanced search
1 file | 1.78 MB Add to list

Improving pixel-based VHR land-cover classifications of urban areas with post-classification techniques

Author
Organization
Abstract
In this paper, three 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. Finally, a region-based filter is applied to reduce high-frequency structural clutter. The three 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.
Keywords
TEXTURE SEGMENTATION, IMAGE SEGMENTATION, COEFFICIENT, MODELS

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.78 MB

Citation

Please use this url to cite or link to this publication:

MLA
Van de Voorde, Tim, et al. “Improving Pixel-Based VHR Land-Cover Classifications of Urban Areas with Post-Classification Techniques.” PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, vol. 73, no. 9, 2007, pp. 1017–27.
APA
Van de Voorde, T., De Genst, W., & Canters, F. (2007). Improving pixel-based VHR land-cover classifications of urban areas with post-classification techniques. PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 73(9), 1017–1027.
Chicago author-date
Van de Voorde, Tim, William De Genst, and Frank Canters. 2007. “Improving Pixel-Based VHR Land-Cover Classifications of Urban Areas with Post-Classification Techniques.” PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING 73 (9): 1017–27.
Chicago author-date (all authors)
Van de Voorde, Tim, William De Genst, and Frank Canters. 2007. “Improving Pixel-Based VHR Land-Cover Classifications of Urban Areas with Post-Classification Techniques.” PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING 73 (9): 1017–1027.
Vancouver
1.
Van de Voorde T, De Genst W, Canters F. Improving pixel-based VHR land-cover classifications of urban areas with post-classification techniques. PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING. 2007;73(9):1017–27.
IEEE
[1]
T. Van de Voorde, W. De Genst, and F. Canters, “Improving pixel-based VHR land-cover classifications of urban areas with post-classification techniques,” PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, vol. 73, no. 9, pp. 1017–1027, 2007.
@article{8645241,
  abstract     = {In this paper, three 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. Finally, a region-based filter is applied to reduce high-frequency structural clutter. The three 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.},
  author       = {Van de Voorde, Tim and De Genst, William and Canters, Frank},
  issn         = {0099-1112},
  journal      = {PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING},
  keywords     = {TEXTURE SEGMENTATION,IMAGE SEGMENTATION,COEFFICIENT,MODELS},
  language     = {eng},
  number       = {9},
  pages        = {1017--1027},
  title        = {Improving pixel-based VHR land-cover classifications of urban areas with post-classification techniques},
  volume       = {73},
  year         = {2007},
}

Web of Science
Times cited: