Rain Removal Using Kalman Filter in Video

Park, Wan-Joo; Lee, Kwae-Hi

doi:10.1109/icsma.2008.4505573

Cited by 40 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To deal with the noise variance problem in HEVC codec, various models and frameworks are proposed to remove the highly correlated rain streaks present in the HD video sequence. Innovative filtering methods are proposed in [13, 14], the noise pattern is eliminated by performing pre‐filtering of the corrupted noisy video sequence. Hence, such a filtering method provides considerable improvement in the quality of video sequence which depends on noise variance.…”

Section: Related Workmentioning

confidence: 99%

Investigation of filtering of rain streaks affected video sequences under various quantisation parameter in HEVC encoder using an enhanced V‐BM4D algorithm

Jayaraman¹,

Chinnusamy²

2020

IET Image Processing

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Investigation of filtering of rain streaks affected video sequences under various quantisation parameter in HEVC encoder using an enhanced V‐BM4D algorithm

Jayaraman¹,

Chinnusamy²

2020

IET Image Processing

View full text Add to dashboard Cite

“…The mainstream single image rain removal methods are generally fall into modeldriven traditional methods and data-driven deep learning-based methods [3]. The former focus on sufficiently encoding the physical properties and prior information of rain streaks and background images into an optimization model and designing rational algorithms to recover t-the clean background image [4,5]. The later learn network parameters for attaining complex rain removal functions by designing specific network architectures and precollecting rainy-clean image pairs [6,7,8,9,10,11].…”

Section: Introductionmentioning

confidence: 99%

Lightweight single image deraining algorithm incorporating visual saliency

Yang

2022

Preprint

View full text Add to dashboard Cite

Deep learning (DL) methods have achieved excellent performance in the task of single image rain removal, however, there are still some challenges, such as artifact remnant, background over-smooth, and more and more complex and heavy-weight network architecture. Due to too heavy-weight network to suit outdoor detection devices or mobile devices, therefore, we propose a light-weight single image deraining algorithm incorporating visual attention saliency mechanisms (LDVS). The network consists of dilation convolution module, the convolutional block attention module (CBAM), and gated recursive unit module. Specifically, rain steaks feature maps are extracted by the combinations of dilated convolution with CBAM, which also facilitates accurate localisation of rain steak location, and then the three gated recursive units is cascaded to remove steaks stage by stage. The dilated convolution module and CBAM are used to reduce network’s weight size and retain the rain removal result, thus our LDVS method belongs to the lightweight with only 50703 parameters. Extensive experiments on synthetic and real-world datasets have demonstrated that our method outperforms the baseline both under qualitative and quantitative analysis. Under the same rain removal result, our method is less time cost and less burden.

show abstract

“…This method produced degradation in the perceptual quality of videos with dynamic background. Park and Lee [4] recommended a technique for rain removal in videos using Kalman filter to estimate the background of rain‐affected pixel intensity.…”

Section: Introductionmentioning

confidence: 99%