Motion robust rain detection and removal from videos

Xinwei Xue; Xin Jin; Chenyuan Zhang; Satoshi Goto

doi:10.1109/MMSP.2012.6343435

Motion robust rain detection and removal from videos

Xinwei Xue^*, Xin Jin, Chenyuan Zhang, Satoshi Goto

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Citations (Scopus)

Abstract

Weather such as rain and snow cause difficulties in processing the videos captured. Since the appearance of rain drops can affect the performance of human tracking and reduce the efficiency of video compression, detection and removal of rain is a challenging problem in outdoor surveillance systems. In this paper, we propose a new algorithm for rain detection, which is based on joint spatial and wavelet domain features. This approach is robust to the videos with moving objects in the rain. Experimental results demonstrated its better performance in comparison with the existing approaches in the subjective quality.

Original language	English
Title of host publication	2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Proceedings
Pages	170-174
Number of pages	5
DOIs	https://doi.org/10.1109/MMSP.2012.6343435
Publication status	Published - 2012
Event	2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Banff, AB Duration: 2012 Sept 17 → 2012 Sept 19

Other

Other	2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012
City	Banff, AB
Period	12/9/17 → 12/9/19

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Signal Processing

Access to Document

10.1109/MMSP.2012.6343435

Cite this

@inproceedings{bc135840e049443f882533a5a5e8d94c,

title = "Motion robust rain detection and removal from videos",

abstract = "Weather such as rain and snow cause difficulties in processing the videos captured. Since the appearance of rain drops can affect the performance of human tracking and reduce the efficiency of video compression, detection and removal of rain is a challenging problem in outdoor surveillance systems. In this paper, we propose a new algorithm for rain detection, which is based on joint spatial and wavelet domain features. This approach is robust to the videos with moving objects in the rain. Experimental results demonstrated its better performance in comparison with the existing approaches in the subjective quality.",

author = "Xinwei Xue and Xin Jin and Chenyuan Zhang and Satoshi Goto",

year = "2012",

doi = "10.1109/MMSP.2012.6343435",

language = "English",

isbn = "9781467345729",

pages = "170--174",

booktitle = "2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Proceedings",

note = "2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 ; Conference date: 17-09-2012 Through 19-09-2012",

}

TY - GEN

T1 - Motion robust rain detection and removal from videos

AU - Xue, Xinwei

AU - Jin, Xin

AU - Zhang, Chenyuan

AU - Goto, Satoshi

PY - 2012

Y1 - 2012

N2 - Weather such as rain and snow cause difficulties in processing the videos captured. Since the appearance of rain drops can affect the performance of human tracking and reduce the efficiency of video compression, detection and removal of rain is a challenging problem in outdoor surveillance systems. In this paper, we propose a new algorithm for rain detection, which is based on joint spatial and wavelet domain features. This approach is robust to the videos with moving objects in the rain. Experimental results demonstrated its better performance in comparison with the existing approaches in the subjective quality.

AB - Weather such as rain and snow cause difficulties in processing the videos captured. Since the appearance of rain drops can affect the performance of human tracking and reduce the efficiency of video compression, detection and removal of rain is a challenging problem in outdoor surveillance systems. In this paper, we propose a new algorithm for rain detection, which is based on joint spatial and wavelet domain features. This approach is robust to the videos with moving objects in the rain. Experimental results demonstrated its better performance in comparison with the existing approaches in the subjective quality.

UR - http://www.scopus.com/inward/record.url?scp=84870609383&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870609383&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2012.6343435

DO - 10.1109/MMSP.2012.6343435

M3 - Conference contribution

AN - SCOPUS:84870609383

SN - 9781467345729

SP - 170

EP - 174

BT - 2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Proceedings

T2 - 2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012

Y2 - 17 September 2012 through 19 September 2012

ER -

Motion robust rain detection and removal from videos

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this