Intelligent video event detection for surveillance systems

Abstract

In recent years, real-time direct detection of events by surveillance systems has attracted a great deal of attention. In this chapter, we present solutions for video-based surveillance systems in the spatial domain and in the compressed domain, respectively. In spatial domain, we propose a new video-based surveillance system that can perform real-time event detection. In the background modelling phase, we adopt a mixture of Gaussian approach to determine the background. Meanwhile, we use color blob-based tracking to track foreground objects. Due to the self-occlusion problem, the tracking module is designed as a multi-blob tracking process to obtain similar multiple trajectories. We devise an algorithm to merge these trajectories into a representative one. After applying the Douglas-Peucker algorithm to approximate a trajectory, we can compare two arbitrary trajectories. The above mechanism enables us to conduct real-time event detection if a number of wanted trajectories are pre-stored in a video surveillance system. In compressed domain, we propose the use of motion vectors embedded in MPEG bitstreams to generate so called motion-flows, which are applied to perform quick video retrieval. By using the motion vectors directly, we do not need to consider the shape of a moving object and its corresponding trajectory. Instead, we simply link the local motion vectors across consecutive video frames to form motion flows, which are then annotated and stored in a video database. In the video retrieval phase, we propose a new matching strategy to execute the video retrieval task. Motions that do not belong to the mainstream motion flows are filtered out by our proposed algorithm. The retrieval process can be triggered by a query-by-sketch (QBS) or a query-by-example (QBE). The experimental results show that our method is efficient and accurate in the video retrieval process. © Springer-Verlag Berlin Heidelberg 2007.