A 18.42 times faster video encoder based on Retinex theory

Xin Jin, Satoshi Goto

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

Abstract

Because of the limitation in the imaging system, videos captured by mobile devices are usually noisy. In this paper, a noise robust fast video encoding scheme is proposed based on Retinex theory. The reflectance image is estimated in a co-analysis module by Retinex theory, within which the content similarity is detected to conduct the encoding process. Experimental results demonstrate that the proposed encoding scheme provides an average of 18.42 times higher encoding speed relative to the existing approaches without sacrificing the subjective quality.

Original languageEnglish
Title of host publication2012 Picture Coding Symposium, PCS 2012, Proceedings
Pages473-476
Number of pages4
DOIs
Publication statusPublished - 2012
Event29th Picture Coding Symposium, PCS 2012 - Krakow
Duration: 2012 May 72012 May 9

Other

Other29th Picture Coding Symposium, PCS 2012
CityKrakow
Period12/5/712/5/9

Fingerprint

Mobile devices
Imaging systems

Keywords

  • Noise robust technique
  • Retinex theory
  • similarity detection
  • video coding

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Jin, X., & Goto, S. (2012). A 18.42 times faster video encoder based on Retinex theory. In 2012 Picture Coding Symposium, PCS 2012, Proceedings (pp. 473-476). [6213257] https://doi.org/10.1109/PCS.2012.6213257

A 18.42 times faster video encoder based on Retinex theory. / Jin, Xin; Goto, Satoshi.

2012 Picture Coding Symposium, PCS 2012, Proceedings. 2012. p. 473-476 6213257.

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

Jin, X & Goto, S 2012, A 18.42 times faster video encoder based on Retinex theory. in 2012 Picture Coding Symposium, PCS 2012, Proceedings., 6213257, pp. 473-476, 29th Picture Coding Symposium, PCS 2012, Krakow, 12/5/7. https://doi.org/10.1109/PCS.2012.6213257
Jin X, Goto S. A 18.42 times faster video encoder based on Retinex theory. In 2012 Picture Coding Symposium, PCS 2012, Proceedings. 2012. p. 473-476. 6213257 https://doi.org/10.1109/PCS.2012.6213257
Jin, Xin ; Goto, Satoshi. / A 18.42 times faster video encoder based on Retinex theory. 2012 Picture Coding Symposium, PCS 2012, Proceedings. 2012. pp. 473-476
@inproceedings{5593bd6f4dc6470b96b652c6b79dd89c,
title = "A 18.42 times faster video encoder based on Retinex theory",
abstract = "Because of the limitation in the imaging system, videos captured by mobile devices are usually noisy. In this paper, a noise robust fast video encoding scheme is proposed based on Retinex theory. The reflectance image is estimated in a co-analysis module by Retinex theory, within which the content similarity is detected to conduct the encoding process. Experimental results demonstrate that the proposed encoding scheme provides an average of 18.42 times higher encoding speed relative to the existing approaches without sacrificing the subjective quality.",
keywords = "Noise robust technique, Retinex theory, similarity detection, video coding",
author = "Xin Jin and Satoshi Goto",
year = "2012",
doi = "10.1109/PCS.2012.6213257",
language = "English",
isbn = "9781457720482",
pages = "473--476",
booktitle = "2012 Picture Coding Symposium, PCS 2012, Proceedings",

}

TY - GEN

T1 - A 18.42 times faster video encoder based on Retinex theory

AU - Jin, Xin

AU - Goto, Satoshi

PY - 2012

Y1 - 2012

N2 - Because of the limitation in the imaging system, videos captured by mobile devices are usually noisy. In this paper, a noise robust fast video encoding scheme is proposed based on Retinex theory. The reflectance image is estimated in a co-analysis module by Retinex theory, within which the content similarity is detected to conduct the encoding process. Experimental results demonstrate that the proposed encoding scheme provides an average of 18.42 times higher encoding speed relative to the existing approaches without sacrificing the subjective quality.

AB - Because of the limitation in the imaging system, videos captured by mobile devices are usually noisy. In this paper, a noise robust fast video encoding scheme is proposed based on Retinex theory. The reflectance image is estimated in a co-analysis module by Retinex theory, within which the content similarity is detected to conduct the encoding process. Experimental results demonstrate that the proposed encoding scheme provides an average of 18.42 times higher encoding speed relative to the existing approaches without sacrificing the subjective quality.

KW - Noise robust technique

KW - Retinex theory

KW - similarity detection

KW - video coding

UR - http://www.scopus.com/inward/record.url?scp=84864035856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864035856&partnerID=8YFLogxK

U2 - 10.1109/PCS.2012.6213257

DO - 10.1109/PCS.2012.6213257

M3 - Conference contribution

SN - 9781457720482

SP - 473

EP - 476

BT - 2012 Picture Coding Symposium, PCS 2012, Proceedings

ER -