(This value is the maximum number of times that the ISODATA utility re-clusters the data). In the Processing Options, Maximum Iterations number field, enter the maximum number(24) of iterations you want. Select the K-means Clustering algorithm method and enter the number of class 10.Ĭlick the Color Scheme Options button, check Grayscale, and close the window. Under Clustering, Options turned on Initialize from Statistics option. The Unsupervised Classification dialog open Input Raster File, enters the continuous raster image you want to use (satellite image.img).Ĭheck Output Cluster Layer, and enter a name for the output file in the directory of your choice. In this Tutorial, perform Unsupervised Classification using Erdas Imagine software.Ĭlick Raster tab > Classification group > expend Unsupervised > select Unsupervised Classification. Performing Unsupervised Classification is simpler than a Supervised Classification, because the signatures are automatically generated by the ISODATA algorithm. A Maximum percentage of unchanged pixels has reached between two iterations.The maximum number of iterations has been performed, or. The ISODATA clustering method uses the minimum spectral distance formula to form clusters. Perform Unsupervised Classification in Erdas Imagine in using the ISODATA algorithm. In some cases, it may be more important to identify groups of pixels with similar spectral characteristics than it is to sort pixels into recognizable categories. They are simply clusters of pixels with similar spectral characteristics. These patterns do not necessarily correspond to directly meaningful characteristics of the scene, such as contiguous, easily recognized areas of a particular soil type or land use. You can specify some parameters that the computer uses to uncover statistical patterns that are inherent in the data. Lawrie went on to lead the remote sensing division of Esri, where he reunited with his classmate Jack Dangermond.The Unsupervised training is more computer-automated. After much success, the company was sold to Intergraph. They decided if red was good enough for Coke, it was good enough for Erdas. The Erdas logo was branded in red one night when Lawrie and Bruce were looking out the window of their new office to see the headquarters of Coca Cola, in downtown Atlanta. There was much discussion about the product name and the entire company (about 50 employees) weighed in on the new name. Erdas Imagine was released in approximately 1989, I believe. Data was obtained on 9 track tapes, which were delivered to users through the mail, in response to a paper form and paper check, mailed to the data provider. At the time, Erdas was a command line computer package that ran most efficiently on a PDP-11 or Microvax computer, although the software was transitioning to the DOS based personal computer, with a maximum hard drive capacity of 32 MB. Lawrie and Bruce left Harvard to found Erdas, Inc., while Jack founded Esri. Carl Stienitz, maybe the first professor to teach GIS concepts in the U.S. Both graduated from the Harvard School of Design (Landscape Architecture) under Dr. The company was started by Lawrie Jordan and Bruce Rado, two amazing individuals. At the time it was a start up company in an incubator facility on the campus of Georgia Tech University.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |