What makes segmentation good? A case study in boreal forest habitat mapping

Segmentation goodness evaluation is a set of approaches meant for deciding which segmentation is good. In this study, we tested different supervised segmentation evaluation measures and visual interpretation in the case of boreal forest habitat mapping in Southern Finland. The data used were WorldView-2 satellite imagery, a lidar digital elevation model (DEM), and a canopy height model (CHM) in 2 m resolution. The segmentation methods tested were the fractal net evolution approach (FNEA) and IDRISI watershed segmentation. Overall, 252 different segmentation methods, layers, and parameter combinations were tested. We also used eight different habitat delineations as reference polygons against which 252 different segmentations were tested. The ranking order of segmentations depended on the chosen supervised evaluation measure; hence, no single segmentation could be ranked as the best. In visual interpretation among the several different segmentations that we found rather good, we selected only one as the best. In the literature, it has been noted that better segmentation leads to higher classification accuracy. We tested this argument by classifying 12 of our segmentations with the random forest classifier. It was found out that there is no straightforward answer to the argument, since the definition of good segmentation is inconsistent. The highest classification accuracy (0.72) was obtained with segmentation that was regarded as one of the best in visual interpretation. However, almost similarly high classification accuracies were obtained with other segmentations. We conclude that one has to decide what one wants from segmentation and use segmentation evaluation measures with care.