Distributed image compression for sensor networks using correspondence analysis and super-resolution

We outline a distributed codingtechnique for images captured from sensors with overlapping fields of view in a sensor network. First, images from correlated views are roughly registered (relative to a sensor of primary interest) via a low-bandwidth data-sharing method involving image feahlre points and feature point wrrespondence. An area of overlap is then idenuied, and each sensor transmits a low-resolution version of the common image block to the receiver, amortizing the coding wst for that block among the set of sensors. Super-resolution techniques are finally employed at the receiver to recmstruct a high-resolutionversion of the common block. We discuss the registration and super-resolution techniques used and presentexamplesof each stepin the proposed codingprocess. A numerical analysis illustratingthe potentialcoding benefit follows,and we conclude with a brief discussion of the key issues remaining to be resolved on the path to coder robustness.

• Type: Conference
• Year: 2003
• Where: ICIP
• Authors: R. Wagner, Robert D. Nowak, Richard G. Baraniuk
• Keywords: Common Block, Common Image Block, ICIP 2003, Image Feahlre Points, Image Processing, Low-bandwidth Data-sharing Method, Sensor Network