Mobile objects and sensors within a video surveillance system: Spatio-temporal model and queries

Abstract

The videos recorded by video surveillance systems represent a key element in a police inquiry. Based on a spatio-temporal query specified by a victim, (e.g., the trajectory of the victim before and after the aggression) the human operators select the cameras that could contain relevant information and analyse the corresponding video contents. This task becomes cumbersome because of the huge volume of video contents and the cameras' mobility. This paper presents an approach, which assists the operator in his task and reduces the research space. We propose to model the cameras' network (fixed and mobile cameras) on top of the city's transportation network. We consider the video surveillance system as a multilayer geographic information system, where the cameras are situated into a distinct layer, which is added on top of the other layers (e.g., roads, transport) and is related to them by the location. The model is implemented in a spatio-temporal database. Our final goal is that based on a spatio-temporal query to automatically extract the list of cameras (fixed and mobile) concerned by the query. We propose to include this automatically computed relative position of the cameras as an extension of the standard ISO 22311.