Introduction

The aim of this practical is for you to gain experience in the supervised classification of Eath Observation (EO) imagery, using envi software. At the end of this practical, you should be able to analyse multispectral EO data for the purpose of classsification, derive statical descriptions of training classes, and apply these to achieve categorisation (classification) of the data.

Image data

Refer to the basic UNIX commands page for help if required. Type the following commands :  

machine% cd Data
machine% mkdir classification
machine% cp ~plewis/classification/ETM-* classification
machine% cp ~plewis/classification/TM-* classification
machine% cp ~plewis/classification/SRTM-2002* classification
machine% cd classification
machine% ls -l ETM-* TM-* SRTM-2002*

-rw-r--r--   1 plewis   311040000 Sep 29 15:23 ETM-110801
-rw-r--r--   1 plewis       1237 Sep 29 15:24 ETM-110801.HDR
-rw-r--r--   1 plewis       3339 Sep 29 14:27 ETM-110801.sta
-rw-r--r--   1 plewis   51840000 Sep 29 15:20 SRTM-2002
-rw-r--r--   1 plewis        544 Sep 29 15:20 SRTM-2002.HDR
-rw-r--r--   1 plewis   311040000 Sep 29 15:22 TM-250792
-rw-r--r--   1 plewis       1195 Sep 29 15:25 TM-250792.HDR

1. TM-250792

2. ETM-110801

TM 27th July 1992	ETM 11th August 2001

3. SRTM DEM data

SRTM DEM data

All data were obtained from the GLCF.

Map of region shown on right (from Earthshots)	Satellite data 1975-1992 (from Earthshots)

Urban May also include other 'built' structures such as roads. You should be able to recognise these from their spatial structure, even at this resolution.
Forest This should be easy to spot, but there are sometime clear 'shading' effects (as in this example) that might complicate classification.
Rocks Rocks are quite easily identifiable in the FCC images. You would generally expect them to be static between the two dates.
Rivers There are rivers and other water bodies in the scene, which you will be able to recognise by their shape. They will be difficult to use as training sites as they are quite narrow at this resolution.
Farmland You will see a broad patchwork of areas that have been cleared of forest and used to graze cattle or raise crops.  The areas a quite easy to spot in the FCC images, but might represent a broad spectral class because of the various physical cover types involved.
other You may spot some areas that have rather different spectral properties to most of the other areas. One example is shown here of field-shaped areas (green and purple areas) that might be inferred to be farmland, but are clearly different spectrally to other areas of farmland. We cannot really determine what these areas are from the information available, so you might require an 'other' class to cope with such eventualities.
cloud The images may contain a small amount of cloud or smoke/haze, an example of which is shown here. They are quite easy to recognise visually in the FCC, but may be difficult to classify unless they are quite thick. If there are any thick clouds, you may see cloud shadows on the ground as well.

B. Defining spectral classes

In order to classify the image data you are required to define a set of "signatures" which represent each class. These are then used to "train" the classification algorithm.

Having defined a signature set for each class, you can now use these definitions to define a supervised classification. Various algorithms are available under the Classification->Supervised... menu of envi. As a start, you might like to consider a Maximum Likelihood classification:

Classification->Supervised...->Maximum Likelihood

First, select the image data you wish to classify. If you do not have an ROI file currently open, you will need to open this via the Open->ROI File... option.

You now need to:

a. Decide which classes to use in the classification (Select Classes from Region);

b. Set a probability threshold for the classification (if pixels have less than this probability of being any class, they will be unclassified). You can set a value of None if you like, but something like 75% (0.80) might be more appropriate (perhaps try 'None' first time around).

c. Set a name of output files (Output Result to File) for the Result image and probably the 'Rule image' as well.

 You can preview the result for a limited region (Preview button), then if that looks fine, click 'OK':

Processing the classification may take a while, so whilst you are learning about this, you may choose to work on an image subset (choose Subset Spatially when you choose the image file to use).

You should find an output classified image:

Along with the 'rule' image (if selected). You should examine both output datasets to guage why the classification has worked as it has (the lower the (-ve) value in 'rule' image, the less likely that pixel is to be the particular class, so you might for instance find some areas which are almost as likelt to be two or more different cover types).

After examining these results, you may wish to go back and redefine your classes or choose new classes. Equally, you may like to try out different classification algorithms. You might also try out some unsupervised classification methods and/or the SMACC Endmember Extraction routines in envi, which will attempt to automatically define a set of 'pure' spectral classes (see envi manual and tutorials).

You can output further information for analysis of the result via: Classification->Post Classification->Class Statistics.

D. Accuracy Assessment

Envi is able to calculate a confusion matrix between two classified images or between a classified image and 'ground truth' ROIs. First then, you must generate the ROIs for this purpose.

Once you have this new (independent) ROI dataset, select: Classification->Post Classification->Confusion Matrix->Using Ground Truth ROIs.... Select first the classification image you wish to assess, then in the following dialogue match up the class names of the classified image and the 'ground truth' ROIs:

Clicking 'OK' through the next box results in the confusion matrix being dsiplayed. For example:

Confusion Matrix: /data/rsu_raid_0/plewis/public_html/geog2021/classificationPractical/result 
 
Overall Accuracy = (10287/10427)  98.6573% 
Kappa Coefficient = 0.9792 
 
                  Ground Truth (Pixels) 
    Class           Forest         Rock        Urban         Farm        Total 
 Unclassified            0            0            0            0            0 
Forest [Purpl         2140            0            0            3         2143 
Rock [Blue] 1            0         1337            0           59         1396 
Urban [White]            0            0         1421           64         1485 
Farm [Green]             0            1           13         5389         5403 
        Total         2140         1338         1434         5515        10427 
 
 
                 Ground Truth (Percent) 
    Class           Forest         Rock        Urban         Farm        Total 
 Unclassified         0.00         0.00         0.00         0.00         0.00 
Forest [Purpl       100.00         0.00         0.00         0.05        20.55 
Rock [Blue] 1         0.00        99.93         0.00         1.07        13.39 
Urban [White]         0.00         0.00        99.09         1.16        14.24 
Farm [Green]          0.00         0.07         0.91        97.72        51.82 
        Total       100.00       100.00       100.00       100.00       100.00 
 
 
 
        Class   Commission     Omission          Commission            Omission 
                 (Percent)    (Percent)            (Pixels)            (Pixels) 
Forest [Purpl         0.14         0.00              3/2143              0/2140 
Rock [Blue] 1         4.23         0.07             59/1396              1/1338 
Urban [White]         4.31         0.91             64/1485             13/1434 
Farm [Green]          0.26         2.28             14/5403            126/5515 
 
 
        Class   Prod. Acc.    User Acc.          Prod. Acc.           User Acc. 
                 (Percent)    (Percent)            (Pixels)            (Pixels) 
Forest [Purpl       100.00        99.86           2140/2140           2140/2143 
Rock [Blue] 1        99.93        95.77           1337/1338           1337/1396 
Urban [White]        99.09        95.69           1421/1434           1421/1485 
Farm [Green]         97.72        99.74           5389/5515           5389/5403 

You should make sure that you understand this form of output and what it is telling you about how well your classified image matched your independent 'ground truth' data. Make sure you understand the terms such as 'User' and 'Producer' accuracy and other reported statistics.

You might also like to examine various options for 'post classification filtering', such as clump and seive. See the envi manual for more details on these operators.

Visualisation

If you have time, you may like to visualise either the original data or the classified image overlain on the SRTM topography. To do this:

Topographic->3D Surface View

You may as well set the image resolution to 'full' here. You may also like to increase the vertical exaggeration for 'dramatic effect' (e.g. to 20). Using the tool should be relatively intuitive. If not, read the envi manual on this feature.

References and further Reading:

Cardille Jeffrey A. and Jonathan A. Foley Agricultural land-use change in Brazilian Amazônia between 1980 and 1995: Evidence from integrated satellite and census data Remote Sensing of Environment, Volume 87, Issue 4, 15 November 2003, Pages 551-562

Carlos M. Souza, Jr. Mapping land use of tropical regions from space PNAS 2006 103: 14261-14262

Daniel C. Nepstad, Adalberto Verssimo, Ane Alencar, Carlos Nobre, Eirivelthon Lima, Paul Lefebvre, Peter Schlesinger, Christopher Potter, Paulo Moutinho, Elsa Mendoza, Mark Cochrane, Vanessa Brooks Large-scale impoverishment of Amazonian forests by logging and fire Nature 398, 505 - 508 (08 Apr 1999) Letters to Editor

Douglas C. Morton, Ruth S. DeFries, Yosio E. Shimabukuro, Liana O. Anderson, Egidio Arai, Fernando del Bon Espirito-Santo, Ramon Freitas, and Jeff Morisette Cropland expansion changes deforestation dynamics in the southern Brazilian Amazon PNAS 2006 103: 14637-14641.