Anti-social behavior detection in audio-visual surveillance systems
Kuklyte, Jogile, Kelly, Philip, Ó Conaire, Ciarán, O'Connor, Noel E.ORCID: 0000-0002-4033-9135 and Xu, Li-Qun
(2009)
Anti-social behavior detection in audio-visual surveillance systems.
In: PRAI*HBA - The Workshop on Pattern Recognition and Artificial Intelligence for Human Behaviour Analysis, 9-11 December 2009, Reggio Emilia, Italy.
In this paper we propose a general purpose framework for
detection of unusual events. The proposed system is based on the unsupervised method for unusual scene detection in web{cam images that was introduced in [1]. We extend their algorithm to accommodate data from different modalities and introduce the concept of time-space blocks. In addition, we evaluate early and late fusion techniques for our audio-visual data features. The experimental results on 192 hours of data show that data fusion of audio and video outperforms using a single modality.