Rain streak removal with well-recovered moving objects from video sequences using photometric correlation

Muhammad Rafiqul Islam; Manoranjan Paul; Michael Antolovich

doi:10.1007/978-3-030-39770-8_1

Rain streak removal with well-recovered moving objects from video sequences using photometric correlation

Muhammad Rafiqul Islam, Manoranjan Paul, Michael Antolovich

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

The main challenge in a rain removal algorithm is to differentiate rain streak from moving objects. This paper addresses this problem using the spa-tiotemporal appearance technique (STA). Although the STA-based technique can significantly remove rain from video, in some cases it cannot properly retain all the moving object regions. The photometric feature of rain streak was used to solve this issue. In this paper, a new algorithm combining STA and the photo-metric correlation between rain streak and background is proposed. Rain streak and moving objects were successfully detected and separated by combining both techniques, then fused to obtain well-recovered moving objects with rain-free video. The experimental results reveal that the proposed algorithm significantly outperforms the state-of-the-art methods for both real and synthetic rain streak.

Original language	English
Title of host publication	Image and Video Technology
Subtitle of host publication	PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers
Editors	Joel Janek Dabrowski, Ashfaqur Rahman, Manoranjan Paul
Place of Publication	Cham, Switzerland
Publisher	Springer Nature
Pages	3-13
Number of pages	11
Edition	1
ISBN (Electronic)	9783030397708
ISBN (Print)	9783030397692
DOIs	https://doi.org/10.1007/978-3-030-39770-8_1
Publication status	Published - 2020
Event	9th Pacific-Rim Symposium on Image and Video Technology: PSIVT 2019 - Charles Sturt University Study Centre, Sydney, Australia Duration: 18 Nov 2019 → 22 Nov 2019 http://www.psivt.org/psivt2019/index.html http://www.psivt.org/psivt2019/program.html (program) https://link.springer.com/book/10.1007/978-3-030-34879-3 (proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name
Number	11994

Conference

Conference	9th Pacific-Rim Symposium on Image and Video Technology
Country/Territory	Australia
City	Sydney
Period	18/11/19 → 22/11/19
Other	The Pacific-Rim Symposium on Image and Video Technology (PSIVT) is a premier level biennial series of symposia that aim at providing a forum for researchers and practitioners who are being involved, or are contributing to theoretical advances or practical implementations in image and video technology.
Internet address	http://www.psivt.org/psivt2019/index.html http://www.psivt.org/psivt2019/program.html (program) https://link.springer.com/book/10.1007/978-3-030-34879-3 (proceedings)

Access to Document

10.1007/978-3-030-39770-8_1

Cite this

Islam, M. R., Paul, M., & Antolovich, M. (2020). Rain streak removal with well-recovered moving objects from video sequences using photometric correlation. In J. J. Dabrowski, A. Rahman, & M. Paul (Eds.), Image and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers (1 ed., pp. 3-13). (Lecture Notes in Computer Science). Springer Nature. https://doi.org/10.1007/978-3-030-39770-8_1

Islam, Muhammad Rafiqul ; Paul, Manoranjan ; Antolovich, Michael. / Rain streak removal with well-recovered moving objects from video sequences using photometric correlation. Image and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers. editor / Joel Janek Dabrowski ; Ashfaqur Rahman ; Manoranjan Paul. 1. ed. Cham, Switzerland : Springer Nature, 2020. pp. 3-13 (Lecture Notes in Computer Science).

@inproceedings{6400669cea6149ccb630747a5db65d7a,

title = "Rain streak removal with well-recovered moving objects from video sequences using photometric correlation",

abstract = "The main challenge in a rain removal algorithm is to differentiate rain streak from moving objects. This paper addresses this problem using the spa-tiotemporal appearance technique (STA). Although the STA-based technique can significantly remove rain from video, in some cases it cannot properly retain all the moving object regions. The photometric feature of rain streak was used to solve this issue. In this paper, a new algorithm combining STA and the photo-metric correlation between rain streak and background is proposed. Rain streak and moving objects were successfully detected and separated by combining both techniques, then fused to obtain well-recovered moving objects with rain-free video. The experimental results reveal that the proposed algorithm significantly outperforms the state-of-the-art methods for both real and synthetic rain streak. ",

keywords = "Rain removal, Photometric correlation, Spatiotemporal appearance, Video cleaning",

author = "Islam, {Muhammad Rafiqul} and Manoranjan Paul and Michael Antolovich",

note = "Includes bibliographical references.; 9th Pacific-Rim Symposium on Image and Video Technology : PSIVT 2019 ; Conference date: 18-11-2019 Through 22-11-2019",

year = "2020",

doi = "10.1007/978-3-030-39770-8_1",

language = "English",

isbn = "9783030397692",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "3--13",

editor = "Dabrowski, {Joel Janek} and Ashfaqur Rahman and Manoranjan Paul",

booktitle = "Image and Video Technology",

address = "United States",

edition = "1",

url = "http://www.psivt.org/psivt2019/index.html, http://www.psivt.org/psivt2019/program.html, https://link.springer.com/book/10.1007/978-3-030-34879-3",

}

Islam, MR, Paul, M & Antolovich, M 2020, Rain streak removal with well-recovered moving objects from video sequences using photometric correlation. in JJ Dabrowski, A Rahman & M Paul (eds), Image and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers. 1 edn, Lecture Notes in Computer Science, Springer Nature, Cham, Switzerland, pp. 3-13, 9th Pacific-Rim Symposium on Image and Video Technology, Sydney, New South Wales, Australia, 18/11/19. https://doi.org/10.1007/978-3-030-39770-8_1

Rain streak removal with well-recovered moving objects from video sequences using photometric correlation. / Islam, Muhammad Rafiqul; Paul, Manoranjan ; Antolovich, Michael.
Image and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers. ed. / Joel Janek Dabrowski; Ashfaqur Rahman; Manoranjan Paul. 1. ed. Cham, Switzerland: Springer Nature, 2020. p. 3-13 (Lecture Notes in Computer Science).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Rain streak removal with well-recovered moving objects from video sequences using photometric correlation

AU - Islam, Muhammad Rafiqul

AU - Paul, Manoranjan

AU - Antolovich, Michael

N1 - Includes bibliographical references.

PY - 2020

Y1 - 2020

N2 - The main challenge in a rain removal algorithm is to differentiate rain streak from moving objects. This paper addresses this problem using the spa-tiotemporal appearance technique (STA). Although the STA-based technique can significantly remove rain from video, in some cases it cannot properly retain all the moving object regions. The photometric feature of rain streak was used to solve this issue. In this paper, a new algorithm combining STA and the photo-metric correlation between rain streak and background is proposed. Rain streak and moving objects were successfully detected and separated by combining both techniques, then fused to obtain well-recovered moving objects with rain-free video. The experimental results reveal that the proposed algorithm significantly outperforms the state-of-the-art methods for both real and synthetic rain streak.

AB - The main challenge in a rain removal algorithm is to differentiate rain streak from moving objects. This paper addresses this problem using the spa-tiotemporal appearance technique (STA). Although the STA-based technique can significantly remove rain from video, in some cases it cannot properly retain all the moving object regions. The photometric feature of rain streak was used to solve this issue. In this paper, a new algorithm combining STA and the photo-metric correlation between rain streak and background is proposed. Rain streak and moving objects were successfully detected and separated by combining both techniques, then fused to obtain well-recovered moving objects with rain-free video. The experimental results reveal that the proposed algorithm significantly outperforms the state-of-the-art methods for both real and synthetic rain streak.

KW - Rain removal

KW - Photometric correlation

KW - Spatiotemporal appearance

KW - Video cleaning

U2 - 10.1007/978-3-030-39770-8_1

DO - 10.1007/978-3-030-39770-8_1

M3 - Conference paper

SN - 9783030397692

T3 - Lecture Notes in Computer Science

SP - 3

EP - 13

BT - Image and Video Technology

A2 - Dabrowski, Joel Janek

A2 - Rahman, Ashfaqur

A2 - Paul, Manoranjan

PB - Springer Nature

CY - Cham, Switzerland

T2 - 9th Pacific-Rim Symposium on Image and Video Technology

Y2 - 18 November 2019 through 22 November 2019

ER -

Islam MR, Paul M , Antolovich M. Rain streak removal with well-recovered moving objects from video sequences using photometric correlation. In Dabrowski JJ, Rahman A, Paul M, editors, Image and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18-22, 2019 revised selected papers. 1 ed. Cham, Switzerland: Springer Nature. 2020. p. 3-13. (Lecture Notes in Computer Science). Epub 2020 Jan 27. doi: 10.1007/978-3-030-39770-8_1

Rain streak removal with well-recovered moving objects from video sequences using photometric correlation

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this