SENSE

Smart Embedded Network of Sensing Entities

Grant agreement ID: 033279
Duration: September 2006 – August 2009
Cordis: https://cordis.europa.eu/project/id/033279

Description

The SENSE project (Smart Embedded Network of Sensing Entities) will develop methods, tools and a test platform for the design, implementation and operation of smart adaptive wireless networks of embedded sensing components. The network is an ambient intelligent system which adapts to its environment, creates ad-hoc networks of heterogeneous components, and delivers reliable information to its component sensors and the user. The sensors cooperate to build and maintain a coherent global view from local information. Newly added nodes automatically calibrate themselves to the environment, and share knowledge with neighbours. The network is scalable due to local information processing and sharing, and self-organizes based on the physical placement of nodes. A test platform for a civil security monitoring system will be developed as a test application, composed of video cameras and microphones.

The test platform will be installed in an airport, to yield real data and performance goals from a realistic test environment. Each sensor is a stand-alone system consisting of multiple embedded components: video system, audio system, central processor, power source and wireless networking. The security application will implement object/scenario recognition (e.g. baggage left unattended, people ‘lurking’ in an area). Nodes will recognize local objects, using a combination of video and audio information, and neighbouring nodes will exchange information about objects in a self-organizing network. The result is a global overview of current objects and events observed by the network.

The key innovative aspects are the methods by which the network perceives its environment, fuses these perceptions using local message passing to achieve local and global object recognition, and calibrates itself based on its environment. Challenges include perception, adaptation, and learning, as well as tools to diagnose and maintain a self-adapting distributed network of embedded components.