An image processing device includes: a generating unit that generates, based on a distance image, two-dimensional distribution information indicating a two-dimensional distribution of an object, in which a distance in a horizontal direction, a distance in a depth direction, and a frequency value corresponding to the distances are related; and a labeling unit that conducts a labeling process by conducting search on the two-dimensional distribution information multiple times, detecting a pixel having the frequency value that is more than a predetermined threshold during each search, and assigning a label that is different in each times of search, wherein the labeling unit conducts a first labeling process by selecting a pixel having the frequency value that is more than the threshold from pixels that abut a pixel being searched in a search direction and assigning the label when the label is not assigned to the pixel selected.