A cloud detection method based on color model and undecimated wavelet transformation

A new cloud detection method based on color model and undecimated wavelet transform was proposed for the basic properties of the cloud area on remote sensing images and band features. First of all, modified HSI Color model transformation was applied to original images combined with the band information in order to extract approximate boundary of cloud area. Secondly, as in binary sampling process of wavelet decomposition, there was losing spectral information and texture information problems. In order to solve this, we used undecimated wavelet transform and the normalized double threshold value method to determine the exact boundary of cloud area. At last, our results were assessed using False Recognition Rate and Accuracy. The assessment was compared with cloud detection methods based on wavelet transform and single threshold. The Result means that proposed algorithm has high detection precision.