Event Detection Using an Attention-Based Tracker

In the last decade, significant progress has been made on developing automatic farfield tracking systems. The PETS 2007 dataset provides some interesting event detection challenges. In this paper, we describe a method of bootstrapping a background model in the presence of significant lighting changes. We then use a blob tracker as an attention mechanism for finding tracks of interest, which we temporally extend using the meanshift algorithm. Using only weak human and luggage models (based purely on size), our system performs well at detecting loitering events, and several events involving interactions between actors and their luggage.