Stereo video deraining and desnowing based on spatiotemporal frame warping

Jin Hwan Kim, Jae Young Sim, Chang-Su Kim

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

3 Citations (Scopus)

Abstract

A novel rain (or snow) streak removal algorithm for stereo video sequences is proposed in this work. We observe that rain streaks appear at different locations in spatiotemporally adjacent frames. Thus, to derain a left-view frame, we synthesize it by warping the spatially adjacent right-view frame and the temporally previous and next frames, respectively. We subtract each warped frame from the original frame, and apply the median filter to the three difference images to obtain a reliable rain mask. Then, we remove rain streaks by replacing each rainy pixel value with a weighted average of non-locally neighboring pixel values. Experimental results demonstrate that the proposed algorithm removes rain streaks reliably and recovers original scene contents faithfully.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5432-5436
Number of pages5
ISBN (Electronic)9781479957514
DOIs
Publication statusPublished - 2014 Jan 28

Fingerprint

Rain
Pixels
Median filters
Snow
Masks

Keywords

  • deraining
  • frame warping
  • nonlocal means filtering
  • stereo deraining
  • Video enhancement

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Kim, J. H., Sim, J. Y., & Kim, C-S. (2014). Stereo video deraining and desnowing based on spatiotemporal frame warping. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 5432-5436). [7026099] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7026099

Stereo video deraining and desnowing based on spatiotemporal frame warping. / Kim, Jin Hwan; Sim, Jae Young; Kim, Chang-Su.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 5432-5436 7026099.

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

Kim, JH, Sim, JY & Kim, C-S 2014, Stereo video deraining and desnowing based on spatiotemporal frame warping. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7026099, Institute of Electrical and Electronics Engineers Inc., pp. 5432-5436. https://doi.org/10.1109/ICIP.2014.7026099
Kim JH, Sim JY, Kim C-S. Stereo video deraining and desnowing based on spatiotemporal frame warping. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 5432-5436. 7026099 https://doi.org/10.1109/ICIP.2014.7026099
Kim, Jin Hwan ; Sim, Jae Young ; Kim, Chang-Su. / Stereo video deraining and desnowing based on spatiotemporal frame warping. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 5432-5436
@inproceedings{7608be6c20734075b6285b1a83be0f61,
title = "Stereo video deraining and desnowing based on spatiotemporal frame warping",
abstract = "A novel rain (or snow) streak removal algorithm for stereo video sequences is proposed in this work. We observe that rain streaks appear at different locations in spatiotemporally adjacent frames. Thus, to derain a left-view frame, we synthesize it by warping the spatially adjacent right-view frame and the temporally previous and next frames, respectively. We subtract each warped frame from the original frame, and apply the median filter to the three difference images to obtain a reliable rain mask. Then, we remove rain streaks by replacing each rainy pixel value with a weighted average of non-locally neighboring pixel values. Experimental results demonstrate that the proposed algorithm removes rain streaks reliably and recovers original scene contents faithfully.",
keywords = "deraining, frame warping, nonlocal means filtering, stereo deraining, Video enhancement",
author = "Kim, {Jin Hwan} and Sim, {Jae Young} and Chang-Su Kim",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7026099",
language = "English",
pages = "5432--5436",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Stereo video deraining and desnowing based on spatiotemporal frame warping

AU - Kim, Jin Hwan

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2014/1/28

Y1 - 2014/1/28

N2 - A novel rain (or snow) streak removal algorithm for stereo video sequences is proposed in this work. We observe that rain streaks appear at different locations in spatiotemporally adjacent frames. Thus, to derain a left-view frame, we synthesize it by warping the spatially adjacent right-view frame and the temporally previous and next frames, respectively. We subtract each warped frame from the original frame, and apply the median filter to the three difference images to obtain a reliable rain mask. Then, we remove rain streaks by replacing each rainy pixel value with a weighted average of non-locally neighboring pixel values. Experimental results demonstrate that the proposed algorithm removes rain streaks reliably and recovers original scene contents faithfully.

AB - A novel rain (or snow) streak removal algorithm for stereo video sequences is proposed in this work. We observe that rain streaks appear at different locations in spatiotemporally adjacent frames. Thus, to derain a left-view frame, we synthesize it by warping the spatially adjacent right-view frame and the temporally previous and next frames, respectively. We subtract each warped frame from the original frame, and apply the median filter to the three difference images to obtain a reliable rain mask. Then, we remove rain streaks by replacing each rainy pixel value with a weighted average of non-locally neighboring pixel values. Experimental results demonstrate that the proposed algorithm removes rain streaks reliably and recovers original scene contents faithfully.

KW - deraining

KW - frame warping

KW - nonlocal means filtering

KW - stereo deraining

KW - Video enhancement

UR - http://www.scopus.com/inward/record.url?scp=84930506863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930506863&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7026099

DO - 10.1109/ICIP.2014.7026099

M3 - Conference contribution

AN - SCOPUS:84930506863

SP - 5432

EP - 5436

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -