Double fidelity terms unidirectional variation model for single-image rain removal

Zhang, Xin; Zhang, Jianwei; Chen, Weibin; Hu, Mingxiao; Zhang, Xiaoqin

doi:10.1117/1.jei.28.2.023015

Cited by 2 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Garg and Nayar ( 2004 ) first exploited the dynamic motion of raindrops with irradiance constraints to remove rain streaks from videos. Since then, researchers have proposed many methods that are based on the priors of rain streaks on photometric appearance (Shen and Xue, 2011 ; Tripathi and Mukhopadhyay, 2011 ), frequency domain (Barnum et al, 2007 , 2010 ), repetitive and discontinuous local patterns (Li M. et al, 2018 ), temporal correlations (Kim J.-H. et al, 2015 ), joint spatial and wavelet domain features (Xue et al, 2012 ; Zhang et al, 2019 ), and spatial discriminatively (Jiang et al, 2017 ). Moreover, methods depending on the matrix decomposition (Ren et al, 2017 ), Gaussian Mixture Model (GMM) distribution (Chen and Chau, 2013 ), and the low-rank property of rain free scenes (Abdel-Hakim, 2014 ; Kim J.-H. et al, 2015 ) have also been presented.…”

Section: Introductionmentioning

confidence: 99%

A Novel Rain Removal Approach for Outdoor Dynamic Vision Sensor Event Videos

et al. 2022

Self Cite

View full text Add to dashboard Cite

As bio-inspired vision devices, dynamic vision sensors (DVS) are being applied in more and more applications. Unlike normal cameras, pixels in DVS independently respond to the luminance change with asynchronous output spikes. Therefore, removing raindrops and streaks from DVS event videos is a new but challenging task as the conventional deraining methods are no longer applicable. In this article, we propose to perform the deraining process in the width and time (W-T) space. This is motivated by the observation that rain steaks exhibits discontinuity in the width and time directions while background moving objects are usually piecewise smooth along with both directions. The W-T space can fuse the discontinuity in both directions and thus transforms raindrops and streaks to approximately uniform noise that are easy to remove. The non-local means filter is adopted as background object motion has periodic patterns in the W-T space. A repairing method is also designed to restore edge details erased during the deraining process. Experimental results demonstrate that our approach can better remove rain noise than the four existing methods for traditional camera videos. We also study how the event buffer depth and event frame time affect the performance investigate the potential implementation of our approach to classic RGB images. A new real-world database for DVS deraining is also created and shared for public use.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Rain Removal Approach for Outdoor Dynamic Vision Sensor Event Videos

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, data labelling is a task that requires a lot of manual work [21][22][23]. Finally, the inappropriate model and imbalanced training data are difficult to get better classification accuracy [24][25][26][27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

A New Classification Method in Ultrasound Images of Benign and Malignant Thyroid Nodules Based on Transfer Learning and Deep Convolutional Neural Network

Chen

Liu

et al. 2021

Complexity

Self Cite

View full text Add to dashboard Cite

Thyroid nodule is a clinical disorder with a high incidence rate, with large number of cases being detected every year globally. Early analysis of a benign or malignant thyroid nodule using ultrasound imaging is of great importance in the diagnosis of thyroid cancer. Although the b-mode ultrasound can be used to find the presence of a nodule in the thyroid, there is no existing method for an accurate and automatic diagnosis of the ultrasound image. In this pursuit, the present study envisaged the development of an ultrasound diagnosis method for the accurate and efficient identification of thyroid nodules, based on transfer learning and deep convolutional neural network. Initially, the Total Variation- (TV-) based self-adaptive image restoration method was adopted to preprocess the thyroid ultrasound image and remove the boarder and marks. With data augmentation as a training set, transfer learning with the trained GoogLeNet convolutional neural network was performed to extract image features. Finally, joint training and secondary transfer learning were performed to improve the classification accuracy, based on the thyroid images from open source data sets and the thyroid images collected from local hospitals. The GoogLeNet model was established for the experiments on thyroid ultrasound image data sets. Compared with the network established with LeNet5, VGG16, GoogLeNet, and GoogLeNet (Improved), the results showed that using GoogLeNet (Improved) model enhanced the accuracy for the nodule classification. The joint training of different data sets and the secondary transfer learning further improved its accuracy. The results of experiments on the medical image data sets of various types of diseased and normal thyroids showed that the accuracy rate of classification and diagnosis of this method was 96.04%, with a significant clinical application value.

show abstract

Double fidelity terms unidirectional variation model for single-image rain removal

Cited by 2 publications

References 26 publications

A Novel Rain Removal Approach for Outdoor Dynamic Vision Sensor Event Videos

A Novel Rain Removal Approach for Outdoor Dynamic Vision Sensor Event Videos

A New Classification Method in Ultrasound Images of Benign and Malignant Thyroid Nodules Based on Transfer Learning and Deep Convolutional Neural Network

Contact Info

Product

Resources

About