Supervised Classification Part 1
Land cover classification of remote sensing imagery is a task which falls into the general category of pattern recognition. Pattern recognition problems, in turn, are usually approached by developing appropriate machine learning algorithms. Broadly speaking, machine learning involves tasks for which there is no known direct method to compute a desired output from a set of inputs. The strategy adopted is for the computer to “learn” from a set of representative examples.
In the case of supervised classification, the task can often be seen as one of modeling probability distributions. On the basis of representative data for K land cover classes presumed to be present in a scene, the a posteriori probabilities ...
Get Image Analysis, Classification and Change Detection in Remote Sensing, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
