SAVASA project @ TRECVID 2012: interactive surveillance event detection
Little, Suzanne and Jargalsaikhan, Iveel and Clawson, Kathy and Li, Hao and Nieto, Marcos and Direkoglu, Cem and O'Connor, Noel E. and Smeaton, Alan F. and Rodriguez, Aitor and Sanchez, Pedro and Villarroel Peniza, Karina and Martinez Llorens, Ana and Gimenez, Roberto and Santos de la Camara, Raul and Mereu, Anna (2012) SAVASA project @ TRECVID 2012: interactive surveillance event detection. In: Text REtrieval Conference Video (TRECVid) Workshop, 26-28 Nov 2012 , Gaithersburg, Maryland, USA.
Full text available as:
In this paper we describe our participation in the interactive surveillance event detection task at TRECVid 2012. The system we developed was comprised of individual classifiers brought together behind a simple video search interface that enabled users to select relevant segments based on down~sampled animated gifs. Two types of user -- `experts' and `end users' -- performed the evaluations. Due to time constraints we focussed on three events -- ObjectPut, PersonRuns and Pointing -- and two of the five available cameras (1 and 3). Results from the interactive runs as well as discussion of the performance of the underlying retrospective classifiers are presented.
Archive Staff Only: edit this record