Abstract
This paper provides new insights into robust human track- ing and semantic event detection within the context of a novel real-time video surveillance system capable of automatically detecting drowning incidents in a swimming pool. An efiective background model that in- corporates prior knowledge about swimming pools and aquatic environ- ments enables swimmers to be reliably detected and tracked despite the significant presence of water ripples, splashes and shadows. Visual indi- cators of water crises are identified based on professional knowledge of water crisis recognition and modelled by a hierarchical set of carefully chosen swimmer descriptors. An efiective alarm generation methodology is then developed to enable the timely detection of genuine water crises while minimizing the number of false alarms. The system has been tested on numerous instances of simulated water crises and potential false alarm scenarios with encouraging results.