In order to extract a feature suitable for comparison, the information processing device according to the present invention comprises: a prediction unit which, on the basis of the positional relationship between a plurality of objects detected and tracked in an input video and on the basis of the overlap between the plurality of objects, predicts the qualities of features extracted from the objects; a selection unit which selects, from among the plurality of objects, only those objects or that object for which the qualities of features predicted by the prediction unit satisfy a prescribed condition; and a feature extraction unit which extracts features from the objects or the object selected by the selection unit.