A Novel Retinex-Based Fractional-Order Variational Model for Images With Severely Low Light

Gu, Zhaochang; Li, Fang; Fang, Faming; Zhang, Guixu

doi:10.1109/tip.2019.2958144

Cited by 82 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional low-light image enhancement methods can be roughly divided into two categories: histogram equalisation (HE)-based methods [28][29][30][31] and Retinex-based methods [32][33][34][35][36][37][38]. It is likely that the simplest and most widely used method for lightening dark images is to directly magnify the low-light image using HE transform, which constructs a histogram of the whole image that is as balanced as possible.…”

Section: Low-light Image Enhancementmentioning

confidence: 99%

Channel splitting attention network for low‐light image enhancement

Pang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Low-light enhancement is a crucial task in computer vision because of the limited dynamic range of digital imaging devices in poor lighting conditions. Images taken under low-light conditions often suffer from insufficient brightness and severe noise. At present, many models based on convolutional neural networks have been proposed to enhance low-light images. However, most models treat the features on different channels equally, which is not conducive to models learning hierarchical features. Consequently, the method proposed a channel splitting attention network (CSAN) that divides the shallow features into two branches, the residual and dense branches, transmitting different information. Residual branching facilitates feature reuse, while dense branching promotes the exploration of new features. In addition, CSAN uses merge-and-run mappings to assist information integration between different branches and distinguishes the information contained in different branch features through an attention module designed in this paper. Multiple experiment results show that the method proposed is superior to state-of-the-art methods in qualitative and quantitative evaluation. Furthermore, CSAN can better suppress chromaticity aberration while enhancing low-light images.

show abstract

Section: Low-light Image Enhancementmentioning

confidence: 99%

Channel splitting attention network for low‐light image enhancement

Pang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…according to Figure 1, after determining the dynamical equations of the system with the fault, the next important step is to define a stable observer for the system (1). For this purpose, the observer F has been designed as (7).…”

Section: System Description and Problem Statementmentioning

confidence: 99%

“…To have a robust FD system, the design should be carried out in such a way that the following conditions are established:  The observer (7) must be designed such that asymptotically stability of the augmented system (8) is guaranteed. To achieve this condition,…”

Section: System Description and Problem Statementmentioning

confidence: 99%

An LMI approach to Mixed H_∞/H_- fault detection observer design for linear fractional-order systems

Azimi

Shandiz

2021

TELKOMNIKA

View full text Add to dashboard Cite

This study deals with the problem of robust fault detection for linear timeinvariant fractional-order systems (FOSs) assumed to be affected by sensor, actuator and process faults as well as disturbances. The observer-based method was employed to solve the problem, where the detector is an observer. The problem was transformed into the mixed 𝐻 ∞ /𝐻 − robust optimization problem to make the system disturbance-resistant on one hand and fault-sensitive on the other hand. Then, sufficient conditions were obtained to solve the problem in the linear matrix inequality (LMI) mode.Finally, the effectiveness and superiority of the method were demonstrated by simulating the solutions on a single-input multi-output thermal testing bench.

show abstract

“…Due to the low light environment and limited camera equipment, the image has low brightness, low contrast, high noise, color distortion and other problems, which will not only affect the aesthetics of the image and human visual experience, but also reduce the performance of advanced visual tasks using normal light image. In order to effectively improve the quality of low-light images, scholars have proposed many low-light image enhancement algorithms, which contains three stages: gray scale transformation, retinal cortex theory, and deep neural network (Fukushima, 1980 ; Gu et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement

Zhang

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

With the development of computer vision, high quality images with rich information have great research potential in both daily life and scientific research. However, due to different lighting conditions, surrounding noise and other reasons, the image quality is different, which seriously affects people's discrimination of the information in the image, thus causing unnecessary conflicts and results. Especially in the dark, the images captured by the camera are difficult to identify, and the smart system relies heavily on high-quality input images. The image collected in low-light environment has the characteristic with high noise and color distortion, which makes it difficult to utilize the image and can not fully explore the rich value information of the image. In order to improve the quality of low-light image, this paper proposes a Heterogenous low-light image enhancement method based on DenseNet generative adversarial network. Firstly, the generative network of generative adversarial network is realized by using DenseNet framework. Secondly, the feature map from low light image to normal light image is learned by using the generative adversarial network. Thirdly, the enhancement of low-light image is realized. The experimental results show that, in terms of PSNR, SSIM, NIQE, UQI, NQE and PIQE indexes, compared with the state-of-the-art enhancement algorithms, the values are ideal, the proposed method can improve the image brightness more effectively and reduce the noise of enhanced image.

show abstract

A Novel Retinex-Based Fractional-Order Variational Model for Images With Severely Low Light

Cited by 82 publications

References 26 publications

Channel splitting attention network for low‐light image enhancement

Channel splitting attention network for low‐light image enhancement

An LMI approach to Mixed H_∞/H_- fault detection observer design for linear fractional-order systems

A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement

Contact Info

Product

Resources

About