Activity Prediction Based on Spatiotemporal Model in a Multiple Cameras Network

This paper considers person re-identification issue in intelligent video surveillance systems. The problem is still difficult because of the large-scale search, especially when there are a huge amount of persons in multi-camera network. We propose a spatiotemporal model based on the statistics of space and time information for object tracking among multiple cameras. This model aims to predict the next camera views where the pedestrians will appear when they disappear from one camera view. So this model can effectively reduce the search scale. Although this model is simple but effective in a real multiple cameras network. In the experiment, it is shown that the model can effectively predict the activity of persons.