FOVEA: A video frame organizer via identity extraction and analysis

In this work we present FOVEA, a system for video sequence indexing based on the identity of appearing subjects. We will detail the features of the single component modules, devoting special attention to classification and clustering. The system presents a number of peculiarities that distinguish it from existing ones. Among these, the account for the concomitant appearance of two subjects in the same clip, and the use of such information in the process of identity mapping. FOVEA was tested on 16 video clips with results that assess both its efficacy and efficiency.