A Research on Single Image Dehazing Algorithms Based on Dark Channel Prior

Alharbi, Ebtesam Mohameed; Ge, Peng; Wang, Hong

doi:10.4236/jcc.2016.42006

Cited by 15 publications

(7 citation statements)

References 18 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from those classic enhancement-based algorithms, the DCP algorithm recovers images based on the fog formatting pattern and performs image defogging with physical mechanisms. Due to its excellent performance, it has been widely used in the field of haze removal and lots of haze removal algorithms based on the DCP algorithm have been proposed in recent years [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Accelerating Haze Removal Algorithm Using CUDA

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The dark channel prior (DCP)-based single image removal algorithm achieved excellent performance. However, due to the high complexity of the algorithm, it is difficult to satisfy the demands of real-time processing. In this article, we present a Graphics Processing Unit (GPU) accelerated parallel computing method for the real-time processing of high-definition video haze removal. First, based on the memory access pattern, we propose a simple but effective filter method called transposed filter combined with the fast local minimum filter algorithm and integral image algorithm. The proposed method successfully accelerates the parallel minimum filter algorithm and the parallel mean filter algorithm. Meanwhile, we adopt the inter-frame atmospheric light constraint to suppress the flicker noise in the video haze removal and simplify the estimation of atmospheric light. Experimental results show that our implementation can process the 1080p video sequence with 167 frames per second. Compared with single thread Central Processing Units (CPU) implementation, the speedup is up to 226× with asynchronous stream processing and qualified for the real-time high definition video haze removal.

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerating Haze Removal Algorithm Using CUDA

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…This empirical observation facilitates the calculation of transmission maps and ultimately the recovery of the haze-less version of the image. This method received a lot of attention and was used and modified by numerous researchers, and recent comparative results [ 25 , 26 , 27 ] show that this DCP-based dehazing technique is still one of the best options to choose from in terms of performance and accuracy on the dehazing task when only a single image is available.…”

Section: Introductionmentioning

confidence: 99%

A Contrast-Guided Approach for the Enhancement of Low-Lighting Underwater Images

2019

View full text Add to dashboard Cite

Underwater images are often acquired in sub-optimal lighting conditions, in particular at profound depths where the absence of natural light demands the use of artificial lighting. Low-lighting images impose a challenge for both manual and automated analysis, since regions of interest can have low visibility. A new framework capable of significantly enhancing these images is proposed in this article. The framework is based on a novel dehazing mechanism that considers local contrast information in the input images, and offers a solution to three common disadvantages of current single image dehazing methods: oversaturation of radiance, lack of scale-invariance and creation of halos. A novel low-lighting underwater image dataset, OceanDark, is introduced to assist in the development and evaluation of the proposed framework. Experimental results and a comparison with other underwater-specific image enhancement methods show that the proposed framework can be used for significantly improving the visibility in low-lighting underwater images of different scales, without creating undesired dehazing artifacts.

show abstract

“…The MSE between two images g(x,y) and f(x,y) is (11) where M and N represent the number of rows and columns respectively.…”

Section: Mean Square Errormentioning

confidence: 99%

“…The approach followed in [10] uses the given depth information to remove haze. In [11] the authors have compared the state-of-the-art in this area and puts forwards their strengths and weaknesses. Through experiments the efficiencies and shortcomings of these algorithms are shared.…”

Section: Introductionmentioning

confidence: 99%

Haze Removal of a Single Image by Using the Brightness Prior

Verma¹,

Kaushik²,

Pathak³

2017

IJIES

View full text Add to dashboard Cite

Abstract:In this paper a novel method for removing haze is given which is based on the Hue Saturation Value color model together with dark channel subtraction. Single image fog/haze removal is a challenging task due to its ill posed nature. As fog/haze increases the brightness of the images captured also increases. In the current wok, a new methodology has been used which involves the subtraction of extra image brightness from the hazy images for keeping the hue and saturation intact. It uses the information of image brightness to get the clear image by histogram equalization. Together, the three approaches of HSV color model, histogram equalization and Dark Channel Subtraction gives clear images. Experimental results are shown in comparison with the state of the art methods. The approach used in the current paper is at par with the current methodologies and the results are better than the existing approaches.

show abstract

A Research on Single Image Dehazing Algorithms Based on Dark Channel Prior

Cited by 15 publications

References 18 publications

Accelerating Haze Removal Algorithm Using CUDA

Accelerating Haze Removal Algorithm Using CUDA

A Contrast-Guided Approach for the Enhancement of Low-Lighting Underwater Images

Haze Removal of a Single Image by Using the Brightness Prior

Contact Info

Product

Resources

About