Temporally coherent real-time video dehazing

Jin Hwan Kim, Won Dong Jang, Yongsup Park, Dong Hahk Lee, Jae Young Sim, Chang-Su Kim

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

8 Citations (Scopus)

Abstract

A real-time video dehazing algorithm, which reduces flickering artifacts and yields high quality output videos, is proposed in this work. Assuming that a scene point yields highly correlated transmission values between adjacent image frames, we develop the temporal coherence cost. Then, we add the temporal coherence cost to the contrast cost and the truncation loss cost to define the overall cost function. By minimizing the overall cost function, we obtain the optimal transmission. Moreover, to reduce the computational complexity and facilitate real-time applications, we approximate the conventional edge preserving filter by the overlapped block filter. Experimental results demonstrate that the proposed algorithm is sufficiently fast for real-time applications and effectively removes haze and flickering artifacts.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages969-972
Number of pages4
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States
Duration: 2012 Sep 302012 Oct 3

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CountryUnited States
CityLake Buena Vista, FL
Period12/9/3012/10/3

Fingerprint

Flickering
Cost functions
Costs
Computational complexity

Keywords

  • contrast enhancement
  • temporal coherence
  • video dehazing
  • Video enhancement

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Kim, J. H., Jang, W. D., Park, Y., Lee, D. H., Sim, J. Y., & Kim, C-S. (2012). Temporally coherent real-time video dehazing. In Proceedings - International Conference on Image Processing, ICIP (pp. 969-972). [6467023] https://doi.org/10.1109/ICIP.2012.6467023

Temporally coherent real-time video dehazing. / Kim, Jin Hwan; Jang, Won Dong; Park, Yongsup; Lee, Dong Hahk; Sim, Jae Young; Kim, Chang-Su.

Proceedings - International Conference on Image Processing, ICIP. 2012. p. 969-972 6467023.

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

Kim, JH, Jang, WD, Park, Y, Lee, DH, Sim, JY & Kim, C-S 2012, Temporally coherent real-time video dehazing. in Proceedings - International Conference on Image Processing, ICIP., 6467023, pp. 969-972, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 12/9/30. https://doi.org/10.1109/ICIP.2012.6467023
Kim JH, Jang WD, Park Y, Lee DH, Sim JY, Kim C-S. Temporally coherent real-time video dehazing. In Proceedings - International Conference on Image Processing, ICIP. 2012. p. 969-972. 6467023 https://doi.org/10.1109/ICIP.2012.6467023
Kim, Jin Hwan ; Jang, Won Dong ; Park, Yongsup ; Lee, Dong Hahk ; Sim, Jae Young ; Kim, Chang-Su. / Temporally coherent real-time video dehazing. Proceedings - International Conference on Image Processing, ICIP. 2012. pp. 969-972
@inproceedings{34962f37f6354d0f903286da0ca1c080,
title = "Temporally coherent real-time video dehazing",
abstract = "A real-time video dehazing algorithm, which reduces flickering artifacts and yields high quality output videos, is proposed in this work. Assuming that a scene point yields highly correlated transmission values between adjacent image frames, we develop the temporal coherence cost. Then, we add the temporal coherence cost to the contrast cost and the truncation loss cost to define the overall cost function. By minimizing the overall cost function, we obtain the optimal transmission. Moreover, to reduce the computational complexity and facilitate real-time applications, we approximate the conventional edge preserving filter by the overlapped block filter. Experimental results demonstrate that the proposed algorithm is sufficiently fast for real-time applications and effectively removes haze and flickering artifacts.",
keywords = "contrast enhancement, temporal coherence, video dehazing, Video enhancement",
author = "Kim, {Jin Hwan} and Jang, {Won Dong} and Yongsup Park and Lee, {Dong Hahk} and Sim, {Jae Young} and Chang-Su Kim",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICIP.2012.6467023",
language = "English",
isbn = "9781467325332",
pages = "969--972",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Temporally coherent real-time video dehazing

AU - Kim, Jin Hwan

AU - Jang, Won Dong

AU - Park, Yongsup

AU - Lee, Dong Hahk

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2012/12/1

Y1 - 2012/12/1

N2 - A real-time video dehazing algorithm, which reduces flickering artifacts and yields high quality output videos, is proposed in this work. Assuming that a scene point yields highly correlated transmission values between adjacent image frames, we develop the temporal coherence cost. Then, we add the temporal coherence cost to the contrast cost and the truncation loss cost to define the overall cost function. By minimizing the overall cost function, we obtain the optimal transmission. Moreover, to reduce the computational complexity and facilitate real-time applications, we approximate the conventional edge preserving filter by the overlapped block filter. Experimental results demonstrate that the proposed algorithm is sufficiently fast for real-time applications and effectively removes haze and flickering artifacts.

AB - A real-time video dehazing algorithm, which reduces flickering artifacts and yields high quality output videos, is proposed in this work. Assuming that a scene point yields highly correlated transmission values between adjacent image frames, we develop the temporal coherence cost. Then, we add the temporal coherence cost to the contrast cost and the truncation loss cost to define the overall cost function. By minimizing the overall cost function, we obtain the optimal transmission. Moreover, to reduce the computational complexity and facilitate real-time applications, we approximate the conventional edge preserving filter by the overlapped block filter. Experimental results demonstrate that the proposed algorithm is sufficiently fast for real-time applications and effectively removes haze and flickering artifacts.

KW - contrast enhancement

KW - temporal coherence

KW - video dehazing

KW - Video enhancement

UR - http://www.scopus.com/inward/record.url?scp=84875859337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875859337&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467023

DO - 10.1109/ICIP.2012.6467023

M3 - Conference contribution

AN - SCOPUS:84875859337

SN - 9781467325332

SP - 969

EP - 972

BT - Proceedings - International Conference on Image Processing, ICIP

ER -