Ré-identification de personnes dans les journaux télévisés basée sur les Histogrammes spatio-temporels
Résumé
In this article, we present a person re-identification in news video approach. It consists of matching the identity of all occurences of a person. Our approach is based on space-time histograms, that are histograms containing, in addition to pixel counts in a video, their position in space and time. Space-time histograms allow a higher precision than classical color histograms during the matching. We have implemented the proposed approach and present a comparison with the results obtained by histograms and spatiograms to bring forward the benefit of considering the time aspects of the video in the modelisation.