Large sets of visual data are now available both, in real time andoff line, at time of investigation in multimedia forensics, however passive querying systems often encounter difﬁculties in retrieving signiﬁcant results. In this paper we propose an iterativeactive querying system for video surveillance and forensic applications based on the continuous interaction between the userand the system. The positive and negative user feedbacks areexploited as the input of a graph based transductive procedurefor iteratively reﬁning the initial query results. Experimentsare shown using people trajectories and people appearance asdistance metrics.
Iterative active querying for surveillance data retrieval in crime detection and forensics / Coppi, Dalia; Calderara, Simone; Cucchiara, Rita. - ELETTRONICO. - (2011), pp. 216-222. (Intervento presentato al convegno International Conference on Imaging for Crime Detection and Prevention, tenutosi a London, UK nel 3-4 Nov. 2011).