Availability of high resolution satellite imagery leads
to a growing number of change detection techniques and algorithms, research is done using remote sensing and
GIS.
In this tutorial, we build on the classification category feature
set by introducing neighborhood relationships and topological functions.
Secondly, we use relative elevation values and fuzzy rules for the
classification systems.
This study demonstrates that the rule-based
classifier is a significantly better approach than the classical per-pixel
classifiers & object based NN method.
 |
| Image Source: NASA |
Methodology
1. Open the eCognition software.
2. Click on “create new project”
option.
3. Import the “Study area image”
from the workspace.
4. Assign weights to NIR band
5. Click on the layers and rename
each layer. Layer 1 as blue, layer 2 as green, and 3rd as red and 4th NIR.
6. Go to “Process” option on the
top toolbar and open “ process tree” All the operations in ecognition are
executed through the “ process tree”
7. Right click in “process tree”
window and open the option “Append new”. Uncheck the “Automatic option” and
type the name “Segmentation” and click OK.
8. The parent class
“segmentation” has been added. Now click the ‘segmentation” option and select
the “Insert child” option to add sub classes.
9. Click the first segmentation
algorithm” Multi Resolution Segmentation”
and select the execute option.
10. Execute next “Multiresolution, Spectral difference”
Note that Execute Multi
Resolution segmentation Scale 70 value -average size of objects Shape (0.4)
weight -Geometric form of the objects Compactness (0.6) Value- The higher the
value, the more compact image objects maybe.
11.
Make classes in class
hierarchy
12.
Create NDVI using formula (NIR-RED/NIR+RED)
13.
Apply threshold
14.
Define other rule set such as
NIR, DN value. Length/width ratio etc….
15.
Export Classes
16. Perform Data Cleansing in
Screenshots are attached at end
Conclusion
Availability of very high spatial and temporal resolution
remote sensing data facilitates mapping highly complex and diverse urban
environments.
In this exercise analyzed and demonstrated the usefulness of combined high
resolution aerial digital images and elevation data, and it’s processing using
object-based image analysis through carefully formed rule set for mapping urban
land covers and quantifying buildings.
In this exercise presents and demonstrates an
approach for formulating an optimal land covers classification rule set over
small representative training urban area image, and its subsequent transfer to
the same, and different multi-sensor, multi-temporal images.
The training area
produced higher classification accuracy because of the less complex urban
features and, there were almost no trees with in the built-up area. There also
was very rigorous selection of the object features for all of the land cover
classes and iterative classification and rules updating. As the test area
becomes larger, multi temporal and multi sensor, so do the variations in the
class characteristics, the increase urban complexity and confusion, and the
rules transition.
Buildings were appropriately classified with the inherited
rules in all of the test areas with an average accuracy. A few dark and magenta
color roof buildings were miss classified as vegetation due to missing height
information in DSM and occlusion by trees. Overall, the height information
helped capture most of the buildings, which otherwise are very diverse in their
spectral and shape characteristics.
References
- K. Leukert, A. Darwish and W. Reinhardt, “Urban Land-cover Classification: An Object-based Perspective,” 2nd Joint Workshop on Remote Sensing and Data Fusion over Urban Areas, Berlin, May 2003.
- P. Mather, Computer processing of remotely-sensed images, Chichester: Wiley, 1999. [3] B. Jähne, Digitale Bildverarbeitung, Berlin: Springer, 1993.
- R. Haralick, L. Shapiro, Computer and robot vision, Vol. 1, Reading, Mass.: Addison-Wesley, 1992.
- Definiens imaging, eCognition user guide [Online]. Available: http://www.definiens-imaging.com/documents/index.htm, April 2003.
- NIMA, Geospatial Standards and Specifications [Online]. Available: http://164.214.2.59/publications/specs/index.html, April 2003.
- Lillesand, T., Kiefer, R., “Remote Sensing and Image Interpretation”, New York, USA: John Wiley & Sons, 2000.
Screenshots
Comments
Post a Comment