A Color Enhancement Scene Estimation Approach for Single Image Haze Removal

Dharejo, Fayaz Ali; Zhou, Yuanchun; Deeba, Farah; Du, Yi

doi:10.1109/lgrs.2019.2951626

Cited by 27 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the aerial images were improved by relying on the YCbCr color space, The proposed method has been compared with several other methods are MSRCR [10], HE [5], DCP [7], Image Entropy, and Information Fidelity (IEIF) [9], and CESE [14]. Four aerial images of type JPG and size (960×1280) were selected, captured from an airspace plane in Iraq were taken from an altitude of less than 5 km as shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Their experiments showed that their approach had satisfactory results in improving aerial images. In many studies, the color correction of compounds has been used as an important basis for enhancement [13], For aerial image enhancement by using Color Enhancement and Scene Estimation (CESE) [14], Fayaz Ali, et al Suggested algorithm includes Enhancement color contrast and color correction depending on Piecewise Linear Transformation (PWLT). All treatments were performed on the RGB compounds individually without the use of color transformation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Aerial Image Enhancement based on YCbCr Color Space

2021

IJIES

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Aerial Image Enhancement based on YCbCr Color Space

2021

IJIES

View full text Add to dashboard Cite

“…Remote sensing has been implemented and overgrowing in super-resolution (SR) technology over the last 20 years. The SISR-based methods are adopted in many imaging applications such as medicine, health, satellite, and surveillance [1][2][3][4]. Remote sensing satellite images [5][6][7] have been widely used in various practical applications such as military applications, envi-This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.…”

Section: Introductionmentioning

confidence: 99%

A plexus‐convolutional neural network framework for fast remote sensing image super‐resolution in wavelet domain

Deeba

Zhou

Dharejo

et al. 2021

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Satellite image processing has been widely used in recent years in a number of applications such as land classification, Identification transfer, resource exploration, super-resolution image, etc. Due to the orbital location, revision time, quick view angle limitations, and weather impact, the satellite images are challenging to manage. There are many types of resolution, such as spatial, spectral, and temporal. Still, in our case, we concentrated on spatial image resolution to super resolve the images from low-resolution images. For remote sensing image super-resolution fast wavelet-based super-resolution (FWSR), we propose a novel, fast wavelet-based plexus framework that performs super-resolution convolutional neural network (SRCNN)-like extraction of features based on three hidden layers. First, wavelet sub-band images are combined into a pre-defined full-scale data training factor, including approximation and interchangeable stand-alone units (frequency subbands). Second, to speed up image recovery, mapping the sub-band image of the wavelet is then measured using its approximate image. Third, the added sub-pixel layer at the end of the network model is intended to reproduce image quality using a plexus framework. The approximation sub-band images obtained after discrete wavelet transform wavelet decomposition are used as input rather than the original image because of their highfrequency data and preserved characteristics. Five current super-resolution neural network approaches are compared with the proposed technique and tested on three pubic satellite image datasets and two benchmark datasets. The experimental findings are well compared qualitatively and quantitatively. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…To minimize this limitation, it is necessary to apply an image quality enhancement [13,14] that emphasizes the brightness contrast of the objects in the image by enhancing the brightness values of other dark areas, excluding those areas that already have large brightness values. Various methods have been studied to overcome the limitations of lowlight areas caused by a counterlight [11][12][13][15][16][17]. One method proposed for brightening a lowilluminance area uniformly distributes the intensity values throughout the intensity histogram equalization of the image [18].…”

Section: Introductionmentioning

confidence: 99%

“…One method proposed for brightening a lowilluminance area uniformly distributes the intensity values throughout the intensity histogram equalization of the image [18]. Research has also been conducted on improving the brightness value of low-light images by applying a retinex-based method [16,19]. To improve the brightness of the image, it is necessary to first determine whether the image contains a counterlight.…”

Section: Introductionmentioning

confidence: 99%

Detection of Road Images Containing a Counterlight Using Multilevel Analysis

Kim

2021

Symmetry

View full text Add to dashboard Cite

In this paper, a method for detecting real-time images that include counterlight produced by the sun, is proposed. It involves applying a multistep analysis of the size, location, and distribution of bright areas in the image. In general, images containing counterlight have a symmetrically high brightness value at a specific location spread over an extremely large region. In addition, the distribution and change in brightness in that specific region have a symmetrically large difference compared with other regions. Through a multistep analysis of these symmetrical features, it is determined whether counterlight is included in the image. The proposed method presents a processing time of approximately 0.7 s and a detection accuracy of 88%, suggesting that the approach can be applied to a safe driving support system for autonomous vehicles.

show abstract

A Color Enhancement Scene Estimation Approach for Single Image Haze Removal

Cited by 27 publications

References 27 publications

Aerial Image Enhancement based on YCbCr Color Space

Aerial Image Enhancement based on YCbCr Color Space

A plexus‐convolutional neural network framework for fast remote sensing image super‐resolution in wavelet domain

Detection of Road Images Containing a Counterlight Using Multilevel Analysis

Contact Info

Product

Resources

About