TY - GEN
T1 - An application of the inpainting algorithm for recovering packet losses from transmitting sequential quad tree compressed images over wireless sensor networks
AU - Stavrou, P.
AU - Nikolakopoulos, G.
AU - Fanakis, N.
AU - Tzes, A.
AU - Theoharis, T.
N1 - Funding Information:
P. Stavrou and T. Theoharis are with the University of Athens, Department of Informatics and Telecommunications p.stavrou(theotheo)@di.uoa.gr G. Nikolakopoulos and A. Tzes are with the University of Patras, Department of Electrical and Computer Engineering, Rio, Achaias, 26500, Greece. gnikolak(tzes)@ece.upatras.gr ★ Author to whom correspondence should be addressed. This research was partially funded by E.U.-European Social Fund and the Greek Ministry of Development-GSRT.
PY - 2009
Y1 - 2009
N2 - In this article an application of the inpainting algorithm for recovering packet losses from transmitting sequential quad tree compressed images over wireless sensor networks is presented. The aim of the proposed scheme is to reconstruct the missing information at the receiver side, based on the inpainting algorithm, instead of increasing the overhead of the network by requesting from the transceiver to re-transmit the lost data packets. The proposed architecture initially compresses the images sequentially using the quad tree decomposition algorithm. In the sequel, at the receiver side, the image is reconstructed as a lossy image, based on the available successfully received data packets, while afterwards the proposed scheme applies the image inpainting algorithm, in order to restore any missing partitions of the image. The inpainting algorithm is performed based on information derived from the the received image itself. Experimental results are presented that prove the efficacy of the proposed scheme.
AB - In this article an application of the inpainting algorithm for recovering packet losses from transmitting sequential quad tree compressed images over wireless sensor networks is presented. The aim of the proposed scheme is to reconstruct the missing information at the receiver side, based on the inpainting algorithm, instead of increasing the overhead of the network by requesting from the transceiver to re-transmit the lost data packets. The proposed architecture initially compresses the images sequentially using the quad tree decomposition algorithm. In the sequel, at the receiver side, the image is reconstructed as a lossy image, based on the available successfully received data packets, while afterwards the proposed scheme applies the image inpainting algorithm, in order to restore any missing partitions of the image. The inpainting algorithm is performed based on information derived from the the received image itself. Experimental results are presented that prove the efficacy of the proposed scheme.
UR - http://www.scopus.com/inward/record.url?scp=79955737117&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79955737117&partnerID=8YFLogxK
U2 - 10.3182/20090921-3-TR-3005.00089
DO - 10.3182/20090921-3-TR-3005.00089
M3 - Conference contribution
AN - SCOPUS:79955737117
SN - 9783902661661
T3 - IFAC Proceedings Volumes (IFAC-PapersOnline)
BT - 2nd IFAC International Conference on Intelligent Control Systems and Signal Processing
PB - IFAC Secretariat
ER -