Morphological profiles used for classification of data from urban areas

Abstract

Summary form only. Classification of panchromatic IKONOS data from an urban area in Reykjavik, Iceland is investigated. It is well known that conventional classification algorithms like the Gaussian maximum likelihood method are not appropriate for classification of high-resolution data from urban areas. Therefore, in the paper, an approach based on morphological pre-processing and neural networks is applied. Several types of morphological transformations were used, each based on compositions of morphological opening and closing transforms. Three data sets were created: A) Data 1: Normal morphological opening and closing operations were used. The size of the structural elements was determined as the size of a square structural element and a quadratic increment step was used. The processed image consisted of the original image, 15 opening channels and 15 closing channels (31 channels in total). The derivative of the morphological profile was also computed, resulting in 30 channels. B) Data 2: Open and closing by reconstruction was used with a linear increment step of 1. The size was the number of connected pixels (the area) of structures, and that was in contrast to Data 1, independent of the shape. The original image, 20 opening channels, and 20 closing channels were classified (41 channels in total). The derivative of the morphological profile was also computed and used in classification, resulting in 40 channels. C) Data 3: Same as Data 2, except, a linear increment step of 2 was used instead of an increment of 1. The classification of these different data sets showed interesting characteristics in classification.