Search icone
Search and publish your papers

Problems associated with unsupervised classification of high resolution imagery ( pictures included )

Or download with : a doc exchange

About the author

student
Level
Advanced
Study
others
School/University
University...

About the document

Published date
Language
documents in English
Format
Word
Type
presentations
Pages
6 pages
Level
Advanced
Accessed
0 times
Validated by
Committee Oboolo.com
0 Comment
Rate this document
  1. Introduction.
  2. Scene information and classification approach.
    1. Difficulties with classifying a QuickBird image.
    2. Division of the scene into two image.
    3. Viewing the resulting image.
  3. Vector mask approach.
    1. Water - the primary feature to be excluded.
    2. Cropping the vector layer.
    3. Creation of a ?water only? image and an ?everything else? image.
  4. Alternative approaches.
    1. Creating buffers around the Wisconsin DNR water body polygons.
    2. Create new water body polygons.
    3. Incorporating a DEM or TIN.
    4. Software designed strictly for the purpose of high resolution image interpretation.
  5. Summary - conclusion.

Early satellite systems with multispectral resolutions on the order of 20m (SPOT 1 ? 4) or 30m (Landsat 4 ? 7) have been able to obtain imagery of sufficient resolution to effectively classify areas with large contiguous areas of information classes, i.e. scenes of dense forest vegetation or cropland. However, accurate classifications of urban areas, where features on the ground change meter by meter, have been impossible to achieve with such lower resolution systems. Satellite systems like Ikonos and QuickBird with resolutions in the panchromatic band at 1 meter and resolutions in the multispectral range of 4 meters produce images of high enough resolution that classification of urban scenes can be done accurately.

[...] Viewing the resulting image (Figure the vast majority of the water and shadow pixels were indeed preserved but a host of asphalt pavement pixels were included in the image as well. Figure 4. Image showing pixels with Red < 230 and NIR < 300; water, shadow, and asphalt pixels visible. (ERDAS Imagine) After checking the DN values of the included asphalt pixels, it was clear that the asphalt pixels' DN values were well within the spectral range of the water and shadow pixels intended to be included in the image. [...]


[...] Pixels at these locations could be separated from the rest of the image as water and problems with the classification would not be nearly as formidable as with other methods. This method would have much the same effect that the vector masking approach would have by avoiding spectral properties as much as possible in removing water pixels. It would also have similar problems, however, in that it would be nearly impossible to remove all water pixels from the image based on DEM characteristics since the resolution of the DEM would most likely be much less than that of the QuickBird image. [...]


[...] (WiscImage) Fully Spectral Approach The same general approach was taken for each of the classification alternatives considered. Before the ISODATA classification, the scene would be divided into two images: one with water/shadows and one with everything else. An ISODATA classification would then be performed on the individual scenes so that water/shadow pixels couldn't ?contaminate? the rest of the image during the classification. Once classified, the two scenes with complementary information classes would be recombined into one image which would effectively be the original image classified into appropriate information classes. [...]

Recent documents in physics & chemistry category

Determination of Heat Capacity Ratio

 Science & technology   |  Physics & chemistry   |  Presentation   |  12/01/2017   |   .doc   |   5 pages

Helicopter control and its general models (PPT presentation)

 Science & technology   |  Physics & chemistry   |  Presentation   |  09/06/2016   |   .ppt   |   29 pages