Polarimetric image recovery method combining histogram stretching for underwater imaging

Li, Xiaobo; Hu, Haofeng; Zhao, Lin; Wang, Hui; Yin, Yaozu; Wu, Lan; Liu, Tiegen

doi:10.1038/s41598-018-30566-8

Cited by 90 publications

(52 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in this study, the structure was distinguished from the background by performing histogram transformation to measure the response of the tubular level gauge. For the histogram transformation, histogram stretching [38,39] and gamma correction [40,41] of Equation 5were applied. Equation 5 When γ is 1, identity transformation is performed.…”

Section: Image Enhancementmentioning

confidence: 99%

Non-Contact Water Level Response Measurement of a Tubular Level Gauge Using Image Signals

Kim

Park

Jeon

et al. 2020

Sensors

View full text Add to dashboard Cite

The occurrence of excessive fluid sloshing during an earthquake can damage structures used to store fluids and can induce secondary disasters, such as environmental destruction and human casualties, due to discharge of the stored fluids. Thus, to prevent such disasters, it is important to accurately predict the sloshing behavior of liquid storage tanks. Tubular level gauges, which visually show the fluid level of a liquid storage tank, are easy to install and economical compared to other water level gauges. They directly show the fluid level and can be applied for various fluids because they can be constructed with various materials according to the fluid characteristics and the intended use. Therefore, in this study, the shaking table test was conducted to verify the validity of the method for measuring the water level response of the tubular level gauge installed on a liquid storage tank using image signals. In addition, image enhancement methods were applied to distinguish between the float installed in the tubular level gauge and the gray level of the background.

show abstract

Section: Image Enhancementmentioning

confidence: 99%

Non-Contact Water Level Response Measurement of a Tubular Level Gauge Using Image Signals

Kim

Park

Jeon

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Histogram stretching (HS) method (Li et al, 2018 ) was chosen due to ease of implementation. HS aims to enhance the contrast by stretching the range of intensity values of two sources of images to the same range, providing the effect of inter-scan normalization.…”

Section: Data Preprocessingmentioning

confidence: 99%

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

et al. 2018

View full text Add to dashboard Cite

Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.

show abstract

“…Many techniques have been proposed to enhance the quality of hazy images through image processing [3], infrared-visible image fusion [4] and polarimetric imaging [5][6][7][8]. These techniques have also been combined together, such as polarimetric imaging with image processing [9,10] and polarimetric imaging with image fusion [11], to further improve the performance. These techniques can effectively enhance the contrast of hazy images captured in scattering media, and even increase the imaging distance [2,12].…”

Section: Introductionmentioning

confidence: 99%

Generalized Polarimetric Dehazing Method Based on Low-Pass Filtering in Frequency Domain

Liang

Ren

et al. 2020

Sensors

View full text Add to dashboard Cite

Polarimetric dehazing methods can significantly enhance the quality of hazy images. However, current methods are not robust enough under different imaging conditions. In this paper, we propose a generalized polarimetric dehazing method based on low-pass filtering in the frequency domain. This method can accurately estimate the polarized state of the scattering light automatically without adjusting bias parameters. Experimental results show the effectiveness and robustness of our proposed method in different hazy weather and scattering underwater environments with different densities. Furthermore, computational efficiency is enhanced more than 70% compared to the polarimetric dehazing method we proposed previously.

show abstract

Polarimetric image recovery method combining histogram stretching for underwater imaging

Cited by 90 publications

References 33 publications

Non-Contact Water Level Response Measurement of a Tubular Level Gauge Using Image Signals

Non-Contact Water Level Response Measurement of a Tubular Level Gauge Using Image Signals

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

Generalized Polarimetric Dehazing Method Based on Low-Pass Filtering in Frequency Domain

Contact Info

Product

Resources

About