Authors:
J. Albusac
;
J. J. Castro-Schez
;
L. Jimenez-Linares
;
D. Vallejo
and
L. M. Lopez-Lopez
Affiliation:
University of Castilla-La Mancha, Spain
Keyword(s):
Artificial Intelligent, Surveillance Systems, Image Understanding, Normality Analysis.
Related
Ontology
Subjects/Areas/Topics:
Advanced Applications of Fuzzy Logic
;
Agents
;
Applications of Expert Systems
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Informatics in Control, Automation and Robotics
;
Intelligent Agents
;
Intelligent Control Systems and Optimization
;
Internet Technology
;
Knowledge Engineering
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Knowledge-Based Systems Applications
;
Software Engineering
;
Symbolic Systems
;
Web Information Systems and Technologies
Abstract:
Recently, there is a growing interest in the development and deployment of intelligent surveillance systems capable of finding out and analyzing simple and complex events that take place on scenes monitored by cameras. Within this context, the use of expert knowledge may offer a realistic solution when dealing with the design of a surveillance system. In this paper, we briefly describe the architecture of an intelligent surveillance system based on normality components and expert knowledge. These components specify how a certain object must ideally behave according to one concept. A specific normality component which analyzes the trajectories followed by objects is studied in depth in order to analyze behaviors in an outdoor environment. The analysis of trajectories in the surveillance context is an interesting issue because any moving object has always a goal in an environment, and it usually goes towards one destination to achieve it.