An informatics-based approach to object tracking for distributed live video computing

Abstract

Omnipresent camera networks have been a popular research topic in recent years. Example applications include surveillance and monitoring of inaccessible areas such as train tunnels and bridges. Though a large body of existing work focuses on image and video processing techniques, very few address the usability of such systems or the implications of real-time video dissemination. In this paper, we present our work on extending the LVDBMS prototype with a multifaceted object model to better characterize objects in live video streams. This forms the basis for a cross camera tracking framework based on the informatics-based approach which permits objects to be tracked from one video stream to another. Queries may be defined that monitor the streams in real time for complex events. Such a new database management environment provides a general-purpose platform for distributed live video computing. © 2011 Springer-Verlag.