Combining Fuzzy C-Mean and Normalized Convolution for Cloud Detection in IR Images
- Cite this paper as:
- Anzalone A., Isgrò F., Tegolo D. (2009) Combining Fuzzy C-Mean and Normalized Convolution for Cloud Detection in IR Images. In: Di Gesù V., Pal S.K., Petrosino A. (eds) Fuzzy Logic and Applications. WILF 2009. Lecture Notes in Computer Science, vol 5571. Springer, Berlin, Heidelberg
An important task for the cloud monitoring in several frameworks is providing maps of the cloud coverage. In this paper we present a method to detect cloudy pixels for images taken from ground by an infra-red camera. The method is a three-steps algorithm mainly based on a Fuzzy C-Mean clustering, that works on a feature space derived from the original image and the output of the reconstructed image obtained via normalized convolution. Experiments, run on several infra-red images acquired under different conditions, show that the cloud maps returned are satisfactory.
KeywordsCloudiness mask fuzzy set infra-red images
Unable to display preview. Download preview PDF.