An Interval-based Query Language for High-level Surveillance Event Detection.
Sven Helmer, Fabio Persia · Open Research (University of Surrey) · 2016
We propose a language based on relational algebra extended by intervals for detecting high-level surveillance events from a video stream. The operators we introduce for describing temporal constraints are based on the well-known Allen's interval relationships. The semantics of our language are clearly defined and we illustrate its usefulness by expressing typical events in it and showing the promising results of an experimental evaluation.