By Topic

Distributed sensor network data fusion using image processing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Elmusrati, M. ; Dept. of Comput. Sci., Vaasa Univ., Finland ; Jantti, R. ; Koivo, H.

In this paper we discuss the analogy between spatial distributed sensor network analysis and image processing. The analogy comes from the fact that in high density sensor networks the output of sensors is correlated both spatially and temporally. This means that the output of a sensor is correlated with the outputs of its neighbours. This characteristic is very similar to the pixels' output (intensity) in video signals. The video signal consists of multiple correlated frames (correlation in time), and each frame consists of large number of pixels, and usually there is high correlation between pixels (spatial correlation). By defining this relation one can use the well-known image processing techniques for sensor data compression, fusion, and analysis. As an example we show how to use the quadtree image decomposition for sensor spatial decomposition.

Published in:

Systems Communications, 2005. Proceedings

Date of Conference:

14-17 Aug. 2005