SEGMENTATION OF SATELLITE IMAGERY USING HIERARCHICAL THRESHOLDING ANDNEURAL NETWORKS

A significant task in the automated interpretation of cloud features o n satellite imagery is the segmentation of the image into separate clo ud features to be identified. A new technique, hierarchical threshold segmentation (HTS), is presented. In HTS, region boundaries are define d over a range of gray-shade thresholds. The hierarchy of the spatial relationships between collocated regions from different thresholds is represented in tree form. This tree is pruned, using a neural network, such that the regions of appropriate sizes and shapes are isolated. T hese various regions from the pruned tree are then collected to form t he final segmentation of the entire image. In segmentation testing usi ng Geostationary Operational Environmental Satellite data, HTS selecte d 94% of 101 dependent sample pruning points correctly, and 93% of 105 independent sample pruning points. Using Advanced Very High Resolutio n Radiometer data, HTS correctly selected 90% of both the 235-case dep endent sample and the 253-case independent sample pruning points. The strength of this approach is that artificial intelligence, that is, re asoning about the sizes and shapes of the emergent regions, is applied during the segmentation process. The neural network component can be trained to respond more favorably to shapes of interest to a particula r analysis problem.