INDEPENDENT COMPONENT ANALYSIS FOR CLASSIFYING MULTISPECTRAL IMAGES WITH DIMENSIONALITY LIMITATION

摘要: Airborne and spaceborne remote sensors can acquire invaluable information about earth surface, which have many important applications. The acquired information usually is represented as two—dimensional grids, ie images. One of techniques to processing such images is Independent Component Analysis (ICA), which is particularly useful for clas-sifying objects with unknown spectral signatures in an unknown image scene, ie unsu-pervised classification. Since the weight matrix in ICA is a square matrix for the purpose of mathematical tractability, the number of objects that can be classified is equal to the data dimensionality, ie the number of spectral bands. When the number of sensors (or spectral channels) is very small (eg a 3—band CIR photograph and 6-band Landsat image with the thermal band being removed), it is impossible to classify all the different objects present in an image scene using the original …