[GIS] Failed to create signature file

arcgis-10.2arcgis-desktopdigital image processingland-classificationremote sensing

I've no clue how to solve this issue in the exercise that I'm trying to perform.

The point where I'm stuck is 4. "Create signature file as LandsatCompS.sgs". I've done what it says in the exercise. I got a error message "Failed to create signature file.

The aim of the exercise is to carry out a supervised image classification of the Northern
half of Jutland.

Start ArcMap and add the Landsat images from the B series (summer images).
Create a composite image composite image for all bands except band 6 – the thermal
band. Save the image as LandsatCompS (S for summer).
Open the orthophotos for land (not urban). Add eventually more orthophotos from the
Geodata library. Try to identify the necessary number of different land cover classes to
cover all areas on the orthophotos. Not more than 15!
Open the Image Classification window, and start digitising training areas. Two for each
class. Create the signature file as LandsatCompS.gsg.
Carry out maximum likelihood classification using LandsatCompS as input raster and LandsatCompS.gsg as signature file. Output is ML_class_NJ1. Use default values for the other inputs.
Put the right colours on the new map and compare with the orthophoto and other maps available for Northern Jutland.
Where are the problems? Try to make an improved classification by increase the number of classes and digitise new training areas. Carry out the classification and assess the result. Which one is best?

Classes

Error message

Landsat Image

Training samples

enter image description here

Best Answer

I had some success by changing the target directory to which I saved the signature file. Rather than using the server space I had been alloted, I chose the local desktop, and it worked without a hitch. Not sure why.

Related Solutions

[GIS] Training signature file for supervised classification in ArcGIS Desktop

I have tried supervised classification in ArcGIS.

Firstly I would say that it is not the best software for classification.

As I did it, you can create training sites as points. Just create a shapefile (or geodatabase), add Integer field, click points over your image and assign classes as numbers. (I think you can also use polygon shapefile).

Training sites

For signatures, go to ArcToolbox > Spatial Analyst Tools > Multivariate > Create Signatures. There just put your bands and training points.

Signatures

ArcGIS doesn't show you the resulting signature file, however it is ASCII file and you can look inside, for example using Notepad++. For each band you can see something like this:

#  Class ID     Number of Cells    Class Name
        1                 5         
# Layers             1             2             3
# Means    
                 74.20000      98.80000      69.60000
# Covariance
    1            67.70000      95.30000     211.60000
    2            95.30000     149.20000     354.40000
    3           211.60000     354.40000     903.80000
# -------------------------------------------------------------------

If you wish, you can plot the Means manually to see if they are separated, for example in Excel.

You can do a dendrogram for your classes Spatial Analyst Tools > Multivariate > Dendrogram.

           Distances between Pairs of Combined Classes
                  (in the sequence of merging)

             Remaining   Merged       Between-Class
               Class      Class          Distance
           -----------------------------------------
                  1          3            1.882214
                  1          4            2.706293
                  1          2           12.502329
           -----------------------------------------

           Dendrogram of c:\2tmp\creates_shallow.gsg

C   DISTANCE
L
A
S  0       1.4     2.8     4.2     5.6     6.9     8.3     9.7    11.1    12.5
S  |-------|-------|-------|-------|-------|-------|-------|-------|-------|

  3 ---------|
             |----|
  1 ---------|    |--------------------------------------------------------|
                  |                                                        |
  4 --------------|                                                        |-
                                                                           |
  2 -----------------------------------------------------------------------|

   |-------|-------|-------|-------|-------|-------|-------|-------|-------|
   0       1.4     2.8     4.2     5.6     6.9     8.3     9.7    11.1    12.5

Then you do actually classification Multivariate > Maximum Likelihood Classification. There you have only two tunable options: to say, how much uncertain pixels will remain unclassified (rejected), and probability weighting for classes; and request a confidence raster.

enter image description here

And the result looks like this:

enter image description here

For theorical information check classification help and signature help.

Actually, after several attempts I switched to Remote Sensing software.

[GIS] How to extract surface from air photo avoiding trees and buildings

I wanted to write a comment, but i don´t have points enough. I think that what you need is to do a classification by texture. Last week i was on a seminar where the aim was to classify images of high resolution with texture and variograms (geostatistics).

you can read this:

http://www.sciencedirect.com/science/article/pii/S0098300499001181
atkinson & lewis. Geostatistical classification for remote sensing: an introduction

i hope this helps you!

Related Question