Unsupervised evaluation method using Markov random field for moving object segmentation in infrared videos

Notice of Removal Scale-constrained unsupervised evaluation method for multi-scale image segmentation

“…In recent studies, more image characteristics have been explored to describe homogeneity or heterogeneity. In [10], the Markov random field model is introduced to measure the contrast between the interior and the exterior of the edge of a segmentation. In [11], the spatial autocorrelation metric, Moran's I, was employed to measure inter-segment goodness.…”