Early segmentation in video compression using CNN processors

K. Laszlo, F. Ziliani, T. Roska, M. Kunt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper two analogic (analog and logic) CNN algorithms are presented which segment a video sequence into objects. The algorithms are mainly based on 3 by 3, linear templates. This allows the CNN Universal Machine to execute the task achieving enormous computation speed (1012 equivalent operation per second). The proposed segmentation algorithms rely on texture and contour information only. They differ in the use or not of the color information. The estimated execution time proves that the proposed segmentation method may be implemented in real time. This result and the quality of the obtained frame description are very appealing in the context of the new video coding standard MPEG-4.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
EditorsV. Tavsanoglu
PublisherIEEE
Pages175-180
Number of pages6
Publication statusPublished - 1998
EventProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA - London, UK
Duration: Apr 14 1998Apr 17 1998

Other

OtherProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA
CityLondon, UK
Period4/14/984/17/98

Fingerprint

Image compression
Motion Picture Experts Group standards
Image coding
Textures
Color

ASJC Scopus subject areas

  • Software

Cite this

Laszlo, K., Ziliani, F., Roska, T., & Kunt, M. (1998). Early segmentation in video compression using CNN processors. In V. Tavsanoglu (Ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 175-180). IEEE.

Early segmentation in video compression using CNN processors. / Laszlo, K.; Ziliani, F.; Roska, T.; Kunt, M.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. ed. / V. Tavsanoglu. IEEE, 1998. p. 175-180.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Laszlo, K, Ziliani, F, Roska, T & Kunt, M 1998, Early segmentation in video compression using CNN processors. in V Tavsanoglu (ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 175-180, Proceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA, London, UK, 4/14/98.
Laszlo K, Ziliani F, Roska T, Kunt M. Early segmentation in video compression using CNN processors. In Tavsanoglu V, editor, Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1998. p. 175-180
Laszlo, K. ; Ziliani, F. ; Roska, T. ; Kunt, M. / Early segmentation in video compression using CNN processors. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. editor / V. Tavsanoglu. IEEE, 1998. pp. 175-180
@inproceedings{ff17ce8f61ba4b31ab931d6b6b4ad1bf,
title = "Early segmentation in video compression using CNN processors",
abstract = "In this paper two analogic (analog and logic) CNN algorithms are presented which segment a video sequence into objects. The algorithms are mainly based on 3 by 3, linear templates. This allows the CNN Universal Machine to execute the task achieving enormous computation speed (1012 equivalent operation per second). The proposed segmentation algorithms rely on texture and contour information only. They differ in the use or not of the color information. The estimated execution time proves that the proposed segmentation method may be implemented in real time. This result and the quality of the obtained frame description are very appealing in the context of the new video coding standard MPEG-4.",
author = "K. Laszlo and F. Ziliani and T. Roska and M. Kunt",
year = "1998",
language = "English",
pages = "175--180",
editor = "V. Tavsanoglu",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - Early segmentation in video compression using CNN processors

AU - Laszlo, K.

AU - Ziliani, F.

AU - Roska, T.

AU - Kunt, M.

PY - 1998

Y1 - 1998

N2 - In this paper two analogic (analog and logic) CNN algorithms are presented which segment a video sequence into objects. The algorithms are mainly based on 3 by 3, linear templates. This allows the CNN Universal Machine to execute the task achieving enormous computation speed (1012 equivalent operation per second). The proposed segmentation algorithms rely on texture and contour information only. They differ in the use or not of the color information. The estimated execution time proves that the proposed segmentation method may be implemented in real time. This result and the quality of the obtained frame description are very appealing in the context of the new video coding standard MPEG-4.

AB - In this paper two analogic (analog and logic) CNN algorithms are presented which segment a video sequence into objects. The algorithms are mainly based on 3 by 3, linear templates. This allows the CNN Universal Machine to execute the task achieving enormous computation speed (1012 equivalent operation per second). The proposed segmentation algorithms rely on texture and contour information only. They differ in the use or not of the color information. The estimated execution time proves that the proposed segmentation method may be implemented in real time. This result and the quality of the obtained frame description are very appealing in the context of the new video coding standard MPEG-4.

UR - http://www.scopus.com/inward/record.url?scp=0031634451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031634451&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031634451

SP - 175

EP - 180

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

A2 - Tavsanoglu, V.

PB - IEEE

ER -