

Will be essential for you to read Chapter 12 in your textbook. Remote sensing literature, cluster analysis is referred to as Unsupervised Procedure is termed cluster analysis by statisticians. N-dimensional set of observations into their natural spectral classes. Statistical techniques are available that can be used to automatically group an It is hard to imagine how the natural groupings of the image values areĬreated in a space that has more than three dimensions. Reference data will come from the site visits done in previous years. Imagery, maps, or site visits) to determine the identity or informationĬlasses of the spectral classes. You mustĬompare classified data to some form of reference data (such as large-scale The identity of the spectral classes will not be initially known. Because they are based on natural groupings of the image values, The classes that result from unsupervised classification are referred to as spectralĬlasses. This process can simultaneously utilize data from multiple bands. Have similar digital numbers), whereas pixels from different cover types shouldīe comparatively well separated in spectral space (i.e. The basic premise is that pixels from the sameĬover type should be close together in the spectral measurement space (i.e. Unlike supervised classification, unsupervised classification does not

Into a number of classes based on natural groupings present in the image Is a method that examines a large number of unknown pixels and divides them

Statistically based approach to identifying various cover types using a processĬalled Unsupervised classification. This exercise will introduce you to a more objective, Identify different cover types in satellite imagery. Introduction: Previous labs have relied on density slicing to Lab IV: Unsupervised Classification with ERDAS
