Visibility of a summary video image is improved. An information processing apparatus generates a summary video image by changing an appearance order of a target object detected from a video image, the information processing apparatus including an identification unit configured to identify an identical target object based on data on a plurality of target objects detected from a video image, a determination unit configured to determine an arrangement of movement paths of two or more target objects identified as an identical target object by the identification unit such that the movement paths do not overlap in a time direction, and a generation unit configured to generate the summary video image of the video image based on the arrangement determined by the determination unit.