What scaling factor to use to convert floating point data into integers to perform the unsupervised classification?
Steps Required for Unsupervised Classification. The user designates1) the number of classes, 2) the maximum number of iterations, 3) the maximum number of times a pixel can be moved from one cluster to another with each iteration, 4) the minimum distance from the mean, and 5) the maximum standard deviation allowable. The program will iterate and recalculate the cluster data until it reaches the iteration threshold designated by the user. Each cluster is chosen by the algorithm and will be evenly distributed across the spectral range maintained by the pixels in the scene. The resulting classification image will approximate that which would be produced with the use of a minimum mean distance classifier. When the iteration thresh-old has been reached the program may require you to rename and save the data clusters as a new file. The display will automatically assign a color to each class;it is possible to alter the color assignments to match an existing color scheme (i.e.,blue = water, green = vegetation, red = urban) after the file has been saved. In the unsupervised classification process, one class of pixels may be mixed and as-signed the color black. These pixels represent values that did not meet the requirements set by the user. This may be attributable to spectral "mixing" represented by the pixel.
Regarding the floating point data, the ceiling value can be taken to make into an integer.
You can try the Google Earth Engine for the unsupervised classification of Landsat images online.
Hi!
Check out this tutorial for a step by step guidance through the entire process with QGIS: http://www.digital-geography.com/unsupervised-classification-in-qgis-kmeans-or-part-two/#.V8fjVVWLRaQ
Best,
Karolina
Thank you Sayan and Karolina for your ansers.
But my question is if I have a surface reflectance image which is floating point (values from 0 to 1) then what rescaling factor should I use (100, 1000 or 10,000) to convert the point data into integer as arcmap wont do unsupervised classification on point data. It requires a valid integer dataset.
Hi again!
According to this site:
http://fromgistors.blogspot.com/2015/01/landsat-8-surface-reflectance.html
the pixel values of Landsat Surface Reflectance High Level Data Product are integer and must be divided by 10,000 in order to obtain the actual reflectance.
So, maybe if you wouold follow the reversed process you perhaps would have your answer...
Best,
Karolina
Hi,
You can convert the values like: 34.567 into 34567, and it's better if you can change the values by writing a simple code.
But, try to be consistent throughout.
Regards,
SM
Thanks Karolina, That was really helpful in taking a decision.
Thank you too Sayan
Follow this link for supervised classification for landsat 8 OLI data
https://www.researchgate.net/publication/301797360_Analyzing_land_surface_temperature_distribution_in_response_to_land_useland_cover_change_using_split_window_algorithm_and_spectral_radiance_model_in_Sundarban_Biosphere_Reserve_India
Article Analyzing land surface temperature distribution in response ...
you can use Envi software and then u can use unsupervised classification
- Badges
- Science topic
- Similar topics
- Geoscience
- Cartography
- Mapping