UNSUPERVISED CLASSIFICATION TECHNIQUES OF SATELLITE IMAGES USING GENETIC ALGORITHM
Traditionally, an unsupervised classification divides all pixels within an image into a corresponding class pixel by pixel; the number of clusters usually needs to be fixed a priori by a human analyst. In general, the spectral properties of specific information classes change with the seasons, and therefore, the relation between object class and spectral cluster is not constant over time. In addition, relations for one image can in general not be extended to others. Thus, even if the number of clusters is correctly fixed for one image at one instance in time, the results cannot be transferred to other areas or epochs. One of the a priori inputs traditionally needed for unsupervised classification is the number of clusters in the data set. In many cases, however, this number of classes is not available. This Matlab design describes a procedure for unsupervised classification based on the application of Genetic Algorithm within unsupervised classification of satellite imagery, which can estimate the required number of clusters as part of the procedure. The effectiveness of the new technique was evaluated using examples of IKONOS satellite image data.
REFERENCES
Reference Paper-1: Genetic Algorithms for the Unsupervised Classification of Satellite Images
Author’s Name: Y. F. Yang, P. Lohmann and, C. Heipke
Source: ISPRS
Year: 2004
You can DOWNLOAD the Matlab code to execute the design.
SIMULATION VIDEO DEMO
If you are looking for customized design development, contact us by WhatsApp @ +91 790 456 8 456 or Email us info@verilogcourseteam.com.