Single nighttime image dehazing based on image decomposition

Liu, Yun; Wang, Anzhi; Zhou, Hao; Jia, Pengfei

doi:10.1016/j.sigpro.2021.107986

Cited by 31 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, deep learning based dehazing has been developed extensively such as DehazeNet [156], MS-CNN [157], AOD-Net [158], Ranking-CNN [159], and coding of contours and colors [160]. At the same time, many new attempts also have been made in dehazing studies such as attention [161] [162], weakly supervised learning [163], self-filtering [164], image decomposition [165], and airlight component etc [166] . Most of them are data-driven methods for natural images, which do not rely too much on the physical model of atmosphere transmission.…”

Section: B Thin Cloud Removalmentioning

confidence: 99%

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

Liu¹

2021

Preprint

View full text Add to dashboard Cite

In the past decades, remote sensing (RS) data fusion has always been an active research community. A large number of algorithms and models have been developed. Generative Adversarial Networks (GAN), as an important branch of deep learning, show promising performances in variety of RS image fusions. This review provides an introduction to GAN for remote sensing data fusion. We briefly review the frequently-used architecture and characteristics of GAN in data fusion and comprehensively discuss how to use GAN to realize fusion for homogeneous RS data, heterogeneous RS data, and RS and ground observation data. We also analyzed some typical applications with GAN-based RS image fusion. This review takes insight into how to make GAN adapt to different types of fusion tasks and summarizes the advantages and disadvantages of GAN-based RS data fusion. Finally, we discuss the promising future research directions and make a prediction on its trends.

show abstract

Section: B Thin Cloud Removalmentioning

confidence: 99%

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

Liu¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…e improved homomorphic filtering method proposed in this paper is tested and compared with the algorithm based on dark channel prior [15] and the contrast limited adaptive histogram equalization (CLAHE) algorithm [16]. e experimental results are shown in Figure 3.…”

Section: Image Preprocessingmentioning

confidence: 99%

Recognition of Tunnel Lining Cracks Based on Digital Image Processing

Dai

Jiang

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Most of the tunnel projects are related to the national economy and people’s livelihood, and their operational safety is of paramount importance. Tunnel safety accidents or hidden safety hazards often start from subtleties. Therefore, the identification of tunnel cracks is a key part of tunnel safety control. The development of computer vision technology has made it possible for the automatic detection of tunnel cracks. Aiming at the problem of low recognition accuracy of existing crack recognition algorithms, this paper uses an improved homomorphic filtering algorithm to dehaze and clear the collected images according to the characteristics of tunnel images and uses an adaptive median filter to denoise the grayscaled image. The extended difference of Gaussian function is used for edge extraction, and the morphological opening and closing operations are used to remove noise. The breakpoints of the binary image are connected after removing the noise to make the image more in line with the actual situation. Aiming at the identification of tunnel crack types, the block index is proposed and used to distinguish linear cracks and network cracks. Using the histogram-like method to distinguish linear cracks in different directions can well solve the mixed crack situation in an image. Compared with the traditional method, the recognition rate of the new algorithm is increased to 94.5%, which is much higher than the traditional crack recognition algorithm. The average processing time of an image is 5.2 s which is moderate, and the crack type discrimination accuracy is more than 92%. In general, the new algorithm has good prospects for theoretical promotion and high engineering application value.

show abstract

“…Photos captured in insufficient illumination conditions such as nighttime, lopsided, under-exposed, etc., exhibit an undesired visual experience or deliver compromised messages for other computer vision tasks, due to their low contrast and lightness and blurry details [ 1 , 2 , 3 , 4 , 5 ]. Especially, high-level computer vision tasks show unsatisfactory performance in these low-light photos, such as in inaccurate face or object recognition [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

“…Low-light image enhancement (LLIE) [ 1 , 8 , 9 , 10 , 11 , 12 , 13 , 14 ] is an efficient way to yield visually pleasing images with moderate lightness, vivid color, and clearer details, so as to further improve the performance of face detection, object recognition, and other tasks. Therefore, LLIE [ 1 , 2 , 3 , 15 ] is an indispensable technology in low-level computer vision applications to generate wanted images.…”

Section: Introductionmentioning

confidence: 99%

FDMLNet: A Frequency-Division and Multiscale Learning Network for Enhancing Low-Light Image

Gong

Liu

et al. 2022

Sensors

View full text Add to dashboard Cite

Low-illumination images exhibit low brightness, blurry details, and color casts, which present us an unnatural visual experience and further have a negative effect on other visual applications. Data-driven approaches show tremendous potential for lighting up the image brightness while preserving its visual naturalness. However, these methods introduce hand-crafted holes and noise enlargement or over/under enhancement and color deviation. For mitigating these challenging issues, this paper presents a frequency division and multiscale learning network named FDMLNet, including two subnets, DetNet and StruNet. This design first applies the guided filter to separate the high and low frequencies of authentic images, then DetNet and StruNet are, respectively, developed to process them, to fully explore their information at different frequencies. In StruNet, a feasible feature extraction module (FFEM), grouped by multiscale learning block (MSL) and a dual-branch channel attention mechanism (DCAM), is injected to promote its multiscale representation ability. In addition, three FFEMs are connected in a new dense connectivity meant to utilize multilevel features. Extensive quantitative and qualitative experiments on public benchmarks demonstrate that our FDMLNet outperforms state-of-the-art approaches benefiting from its stronger multiscale feature expression and extraction ability.

show abstract

Single nighttime image dehazing based on image decomposition

Cited by 31 publications

References 37 publications

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

Recognition of Tunnel Lining Cracks Based on Digital Image Processing

FDMLNet: A Frequency-Division and Multiscale Learning Network for Enhancing Low-Light Image

Contact Info

Product

Resources

About