An eyeball information detection device includes: an acquisition unit configured to acquire a captured image obtained by imaging a region in which there is a probability that a face of an occupant is present in a vehicle by an imaging device provided in proximity to an illumination device that emits light to the region; and a detection unit configured to output eyeball information that corresponds to the captured image by receiving the captured image acquired by the acquisition unit as an input based on a learned model generated by learning a learning image including information similar to the captured image acquired by the acquisition unit and a correct value of the eyeball information on an eyeball of the occupant appearing in the learning image, by machine learning.