Complexity metrics to quantify semantic accuracy in segmented Landsat images

This paper addresses semantic accuracy in relation to images obtained with remote sensing. Semantic accuracy is defined in terms of map complexity. Complexity metrics are applied as a metric to measure complexity. The idea is that a homogeneous map of a low complexity is of a high semantic accuracy. In this study, complexity metrics like aggregation index, fragmentation index and patch size are applied on two images with different objectives, one from an agricultural area in the Netherlands, and one from a rural area in Kazakhstan. Images are segmented first using region merging segmentation. Effects on metrics and semantic accuracy are discussed. On the basis of well-defined subsets, we conclude that the complexity metrics are suitable to quantify the semantic accuracy of the map. Segmentation is the most useful for an agricultural area including various agricultural fields. Metrics are mutually comparable being highly correlated, but showing some different aspects in quantifying map homogeneity and identifying objects of a high semantic accuracy.