VIDEO PROCESSING SYSTEM, VIDEO PROCESSING METHOD, VIDEO PROCESSING DEVICE FOR PORTABLE TERMINAL OR FOR SERVER, AND METHOD FOR CONTROLLING AND PROGRAM FOR CONTROLLING SAME

摘要

The objective of the present invention is to report recognition results in real time for a plurality of recognition subjects in a video while maintaining recognition precision. The present invention is characterized by associating and storing a plurality of recognition subjects with m1 to mk first local feature quantities each comprising a feature vector having from 1 or i1 to ik dimensions, extracting n features from an image in a video, generating n second local feature quantities each comprising a feature vector having from 1 to j dimensions, selecting the lower dimensionality among dimensionality i1 to ik and dimensionality j, and when it has been determined that at least a predetermined fraction of each of the m1 to mk first local feature quantities comprising feature vectors up to the selected dimensionality correspond to the n second local feature quantities comprising feature vectors up to the selected dimensionality, it is recognized that a plurality of recognition subjects of which at least a predetermined fraction correspond are present in the image in the video and information indicating the plurality of recognition subjects is displayed in the image in which the plurality of recognition subjects are present in the video.