Prediction of satellite images using fuzzy rule based Gaussian regression | IEEE Conference Publication | IEEE Xplore

Prediction of satellite images using fuzzy rule based Gaussian regression


Abstract:

We present a novel approach for prediction of satellite image frame that uses a fuzzy rule based framework. The input-output membership functions for the premise and cons...Show More

Abstract:

We present a novel approach for prediction of satellite image frame that uses a fuzzy rule based framework. The input-output membership functions for the premise and consequent parts of the rules are derived using a Gaussian Mixture Model (GMM). The weights of the fuzzy rules are represented as the prior probabilities of the respective Gaussian components. For obtaining the predictive fuzzy model, the GMM parameters are estimated via EM algorithm using a spatiotemporal representation of image sequence or video clips. Minimum Description Length (MDL) criterion is used to obtain a suitable predictive fuzzy model. The resulting model is successfully applied on a sequence of satellite images of tropical cyclone, Nargis, that made landfall in Myanmar on May 2, 2008. The quality of the predicted image is assessed using two criteria. The proposed approach is found to predict image frame successfully.
Date of Conference: 13-15 October 2010
Date Added to IEEE Xplore: 29 April 2011
ISBN Information:

ISSN Information:

Conference Location: Washington, DC, USA

References

References is not available for this document.