Abstract：Cloud type is one of the three elements of cloud observations.And correct identification of cloud type will have a help for analyzing the state of atmospheric motion, providing an important basis for the weather forecast.This paper introduces a preliminary research on cloud classification for whole-sky infrared images by means of the method of image processing.The required characteristic parameters for cloud classification are extracted based on the wavelet transform and texture analysis(GLCM).Then, the suitable classifier for cloud classification is designed and built.The analysis and research work show that comparing a single texture analysis method with the wavelet transform and texture analysis method for the recognition of selected all-sky infrared cloud, the latter has a higher accuracy rate.
LIU L, SUN X, CHEN F, et al.Cloud classification based on structure features of infrared images[J].Journal of Atmospheric and Oceanic Technology, 2011, 28(3): 410-417.
2014, Vol. 31 
