8ParallelpipedClassificationPowerpnts

8ParallelpipedClassificationPowerpnts - Supervised...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Supervised Classification: The Parallelpiped Classification • Unsupervised does not produced good information classes • Tell the classification what classes are important to humans • Golf course example: – Details about golf course are not important but – Golf course versus wet prairie is important • Role of training fields
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Training Fields: A vector tool Digitized Vector Polygon Used like a cookie cutter Saves entire group of rasters under polygon File given land cover name File consists of raster statistics of multidimensional spectral space
Background image of page 2
On Screen (Heads up) digitizing • Uses composite as a map of spectral characteristics • Should be enhanced to bring out details • Once vector polygons are established, training fields are cut from raw data • Composite is simply used as a map for defining training fields • Raw data is source for spectral statistics
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Parametric vs NonParametric Classification • Parametric rules based entirely on statistics – Number of bands – Min and Max values, Mean, St. Dev – Number of rasters – Covariance matrix
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/21/2010 for the course GIS 4037c taught by Professor Roberts during the Spring '10 term at FAU.

Page1 / 10

8ParallelpipedClassificationPowerpnts - Supervised...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online