Trajectory Mining for Activity Analysis[go to overview]
Analysing human activities becomes one of the important research topics in recent years due to the fast and dramatic development of security issues in public spaces. In crowded environments, it is highly important to analyse the activities that arise from people's mobilities. In other words, the activities that can be expressed by the sequential positions of people (trajectories). The reason for this is the theory that these trajectories symbolise high-level interpretation of human activities. However, several factors make studying people's activities based on their mobilities a challenging task. Specifically, the vast diversity of possible activities that people may perform yield to a very complex recognition because of the high inter-class similarity. Furthermore, it is extremely difficult to determine all possible activities that may occur in public spaces. In this presentation, two methods of recognising two different trajectory patterns are presented, namely convoys and suspicious activities. For the first patterns, the trajectories of pedestrians are analysed in order to extract groups of people called "convoys" with a mechanism that ensures their consistency. For the second pattern, the trajectory of a pedestrian is encoded in higher-level features, which are afterwards employed to recognise the general behaviour of its performer.
08.03.18 - 10:15