Skip to Main content Skip to Navigation
Conference papers

Composite Spatio-Temporal Event Detection in Multi-Camera Surveillance Networks

Abstract : In this paper, we present a composite event detection system for multicamera surveillance networks. The proposed framework is able to handle correlations between primitive events that are generated from either a single camera view or multiple camera views with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaves nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent defined rules. The multi-layer design of the composite events provides a great extensibility and flexibility to users in different applications. A standardized XML-style event language is designed to describe the composite events, such that inter-agent communications and event detection module construction are conveniently achieved. In our system, a set of graphical interfaces are developed for users to easily define both primitive and high-level composite events. The proposed system is designed in the distributed form, where different components of the system can be deployed on separate processors and communicating with each other over the network. The capabilities and effectiveness of our system have been demonstrated in several real life applications.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00326779
Contributor : Peter Sturm <>
Submitted on : Sunday, October 5, 2008 - 3:02:31 PM
Last modification on : Monday, October 6, 2008 - 9:17:38 AM
Long-term archiving on: : Monday, October 8, 2012 - 2:00:55 PM

File

1569139696.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00326779, version 1

Collections

Citation

Yun Zhai, Ying-Li Tian, Arun Hampapur. Composite Spatio-Temporal Event Detection in Multi-Camera Surveillance Networks. Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications - M2SFA2 2008, Andrea Cavallaro and Hamid Aghajan, Oct 2008, Marseille, France. ⟨inria-00326779⟩

Share

Metrics

Record views

137

Files downloads

213