Objective The Agentcity vision is: An ambient proactive environment where heterogeneous autonomous and increasingly intelligent systems representing businesses, services and individuals are able to interact with each other in a peer to peer manner and enable flexible and dynamic composition of services. Knowledge, information and service sharing is effectively available to users and organisations. When new pertinent or innovative services are available they are immediately offered to the appropriate user. Services are automatically discovered and integrated at the right level of interaction. Ontology, security, reputation and trust services in the environment should further enrich the range of businesses and private interactions possible between agent peers. Furthermore, the environment should be open to allow new services and systems to be connected and integrated semantically by coming on-line automatically.Objectives:The primary objectives of this project are:(a) to create a realistic, decentralised open environment which enables high level semantic interoperability between systems to support formation of novel, dynamic value constellations,b) to build sufficient knowledge and understanding of dynamic open environments to enable transition to widespread usage in reliable commercial grade systems.The project addresses dynamic value constellations in Four ways:(1) Designing and deploying an open extensible network environment which can support heterogeneous service building blocks composable into new value added service(2) The integration of business services into the environment to support rich interactions(3) The bringing together agent level communication technologies to provide a unified framework for modelling dynamic application services and(4) Demonstration points to show some of the depth and breadth of the world wide network of agent platforms and services.

Main ObjectiveThe objective of MODEST is to define and develop a framework for analysing video sequences in order to extract high-level semantic scene interpretation. This will be based on the segmentation, tracking and indexing of moving objects in video scenes and the index interpretation by the use of Intelligent Physical Agents (IPA). The work will be undertaken within the context of the MPEG-4, MPEG-7 and FIPA standards. The results will be demonstrated by means of a video surveillance application.