The second classifciation method involves "training" the computer to recognize the spectral characteristics of the features that you'd like to identify on the map. Once you've identified the training areas, you ask the software to put the pixels into one of the feature classes or leave in "unclassified." It is never as clean as the textbooks say, for example
The training areas are best made using a RGB image, but they can be transferred to any other file with the same coordinate system (ratios, PCs, etc).
Process Steps.
- pick good training areas
- make sure they are spectrally distinct (how do you do that??)and as homogeneous as possible
- you can pick the regions based on the raw (or stretched at least) bands (top illustration shows a good separation in bands 3 & 4 for VA scene, but poor in bands 1&2),but ratios and PC's will often do better a better job discriminating the training areas (bottom example).
- decide on number of features (lumper or splitter argument)
- Once you have selected training regions, you now need an algorithm to assign pixels from the rest of the image to one of the training region classes. From simplest to most complex, here are the common ways to assign classes to "untrained" pixels. (following image reside at http://nptel.iitm.ac.in)
- parallelpiped - note uncertain regions
- minimum distance to class means
- maximum likelihood
- fuzzy membershipsame as above but with a fuzzy membership rule set.
0 commentaires