International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 43 - Number 23 |
Year of Publication: 2012 |
Authors: R.kalaivani, P.thangaraj |
10.5120/6421-8929 |
R.kalaivani, P.thangaraj . River Water Level Prediction in Satellite Images using Support Vector Machine. International Journal of Computer Applications. 43, 23 ( April 2012), 27-33. DOI=10.5120/6421-8929
In recent days, the impact of satellite image processing in various researches is greater because of the wide variety of applications in astronomy, GIS, Agriculture monitoring and Disaster management. Besides other, the disaster management is important, since it is very useful in protecting the living beings. In this paper, river water level identification is done using support vector machines. In order to achieve this, the input satellite image is preprocessed and subsequently the segmentation is carried out with the aid of the anisotropic diffusion segmentation. Support Vector Machine (SVM) is utilized to identify the river spot in the input image in which contains land also and then the morphological operation is utilized to smooth the image. Consequently, in the testing phase, the image is tested with the SVM for water region identification and also another one SVM is utilized for the identification of the river stage.