Classification and feature extraction for remote sensing images from urban areas based on morphological transformations

TLDR

Panchromatic high‑resolution images contain only a single channel, but applying multiple geodesic opening and closing operations generates many additional channels that may be redundant. The study investigates classification of urban panchromatic images using morphological and neural approaches. The method builds a differential morphological profile from geodesic opening and closing, extracts or selects features via discriminant analysis, decision‑boundary extraction, or index picking, and then feeds the resulting feature set into a neural network for classification on IRS‑1C and IKONOS urban imagery. Experiments show the approach achieves high classification accuracy with only a few features, matching the performance of the full feature space.

Abstract

Classification of panchromatic high-resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is based on three steps. First, the composition of geodesic opening and closing operations of different sizes is used in order to build a differential morphological profile that records image structural information. Although, the original panchromatic image only has one data channel, the use of the composition operations will give many additional channels, which may contain redundancies. Therefore, feature extraction or feature selection is applied in the second step. Both discriminant analysis feature extraction and decision boundary feature extraction are investigated in the second step along with a simple feature selection based on picking the largest indexes of the differential morphological profiles. Third, a neural network is used to classify the features from the second step. The proposed approach is applied in experiments on high-resolution Indian Remote Sensing 1C (IRS-1C) and IKONOS remote sensing data from urban areas. In experiments, the proposed method performs well in terms of classification accuracies. It is seen that relatively few features are needed to achieve the same classification accuracies as in the original feature space.