Identifying Surprising Events in Videos Using Bayesian Topic Models

Automatic processing of video data is essential in order to allow efficient access to large amounts of video content, a crucial point in such applications as video mining and surveillance. In this paper we focus on the problem of identifying interesting parts of the video. Specically, we seek to identify atypical video events, which are the events a human user is usually looking for. To this end we employ the notion of Bayesian surprise, as dened in [1, 2], in which an event is considered surprising if its occurrence leads to a large change in the probability of the world model. We propose to compute this abstract measure of surprise by rst modeling a corpus of video events using the Latent Dirichlet Allocation model. Subsequently, we measure the change in the Dirichlet prior of the LDA model as a result of each video event's occurrence. This change of the Dirichlet prior leads to a closed form expression for an event's level of surprise, which can then be inferred directl...

• Type: Conference
• Year: 2010
• Where: ACCV
• Authors: Avishai Hendel, Daphna Weinshall, Shmuel Peleg
• Keywords: ACCV 2010, LDA Approaches, Surveillance