A Region Merging Segmentation with Local Scale Parameters: Applications to Spectral and Elevation Data

Region merging is the most effective method for the segmentation of remote sensing data. The quality and the size of the resulted image objects is controlled by a global heterogeneity threshold, termed as the scale parameter. However, the multidimensional nature of the visible features in a scene defies the use of an even optimum single global scale parameter. In this study, a novel region merging segmentation method is proposed, where a local scale parameter is defined for each image object by its internal and external heterogeneity measures (i.e., local variance and Moran's I). This method allows image objects with low internal and external heterogeneity to be further merged with higher scale parameter values, since they are more likely to be a part of an adjacent object, than objects with high internal and external heterogeneity. The proposed method was applied in spectral and elevation data and its results were evaluated visually and with supervised and unsupervised evaluation methods. The comparison with multi-resolution segmentation (MRS) showed that the proposed region merging method can produce improved segmentation results in terms of maximizing intra-object homogeneity and inter-object heterogeneity as well as in the delimitation of specific target objects, present in spectral and elevation data. The unsupervised evaluation results of the (1) Cote d'Azur, (2) Manchester, and (3) Szada images from the SZTAKI-INRIA building detection dataset showed that the proposed method (overall goodness, OG(f) (1): 0.7375, (2): 0.7923, (3): 0.7967) performs better than MRS (OG(f) (1): 0.7224, (2): 0.7648, (3): 0.7823). The higher values of OG(f) indicate their ability to produce segmentation results with reduced over-segmentation effects and without the need of presegmented input data, in contrast to the objective heterogeneity and relative homogeneity (OHRH) hybrid segmentation method (OG(f) (1): 0.5864, (2): 0.5151, (3): 0.6983).