The use of morphological profiles in classification of data from urban areas

Classification of panchromatic IKONOS data from an urban area in Reykjavik, Iceland is investigated. It is well known that conventional classification algorithms have difficulty classifying high resolution data from urban areas. Therefore, in the paper, an approach based on morphological preprocessing is applied. The approach is in two steps. First, the morphological composition of geodesic opening and closing operations of different sizes is used in order to build a morphological profile. Although, the original panchromatic data is only of one data channel, the use of the composition operations gives additional data channels, which may contain redundancies. Therefore, in the second step, a neural classifier with pruning capabilities is used to reduce the number of data channels and classify the data. Several compositions of morphological opening and closing transforms where used to obtain a stack of data using differently sized structure elements.

[1]  Jon Atli Benediktsson,et al.  A new approach for the morphological segmentation of high-resolution satellite imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[2]  Jon Atli Benediktsson,et al.  Classification of urban high-resolution satellite imagery using morphological and neural approaches , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[3]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[4]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[5]  L.K. Hansen,et al.  Adaptive regularization of neural classifiers , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[6]  Philippe Salembier,et al.  Connected operators and pyramids , 1993, Optics & Photonics.