Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing

Tang, Ketan; Yang, Jianchao; Wang, Jue

doi:10.1109/cvpr.2014.383

Cited by 507 publications

(331 citation statements)

References 17 publications

Supporting

Mentioning

328

Contrasting

Unclassified

Order By: Relevance

“…We utilize a low-pass Gaussian filter to refine the radiance map [14]. Gaussian filter is a nonlinear filter that smooth's the images.…”

Section: E Gaussian Filtermentioning

confidence: 99%

A Fast Method for Haze Evacuation in Remote Sensing Images by Using Gaussian Filter

Reddy

2018

IJRASET

View full text Add to dashboard Cite

The perceivability of the open air images is degraded on account of terrible climate conditions. Robust solutions to this issue, a simple and novel strategy to take out the haze from satellite remote sensing images using Gaussian filter. The task is challenging due to variations in dark channel prior, air light, transmission map and radiance map. The nearness of haze in the atmosphere degrades the quality of images captured by visible camera sensors. The expulsion of haze is commonly performed under the statistical strategies. Due to haziness, an image generally lost shading and edges. So de hazing strategy restores edge losses and shading impacts seriously. The strategy plays out a per-pixel operation, which is direct to create develop and then apply the Gaussian filter to improve the image quality. Exploratory outcomes show that the proposed strategy can permit a quick execution, it is viable for visual engaging and shading loyalty contrasted with some state-of-the-art methods.

show abstract

“…We utilize a low-pass Gaussian filter to refine the radiance map [14]. Gaussian filter is a nonlinear filter that smooth's the images.…”

Section: E Gaussian Filtermentioning

confidence: 99%

A Fast Method for Haze Evacuation in Remote Sensing Images by Using Gaussian Filter

Reddy

2018

IJRASET

View full text Add to dashboard Cite

show abstract

“…(4), which may cause the dehazing results too dark. Therefore, an adaptive exposure scaling [10] is adopted to adjust brightness for better visual effect. The adaptive exposure map s(x) is first obtained [10]:…”

Section: Brightness Adjustmentmentioning

confidence: 99%

Single Image Haze Removal Using Structure-Aware Atmospheric Veil

Liu

Chen²,

Shang

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we propose a novel and effective haze removal method by using the structure-aware atmospheric veil. More specifically, the initial atmospheric veil is first estimated based on dark channel prior and morphological operator. Furthermore, an energy optimization function considering the structure feature of the input image is constructed to refine the initial atmospheric veil. At last, the haze-free image can be restored by inverting the atmospheric scattering model. Additionally, brightness adjustment is also performed for preventing the dehazing result too dark. Experimental results on hazy images reveal that the proposed method can effectively remove the haze and yield dehazing results with vivid color and high scene visibility.

show abstract

“…Tang et al's method for preparing the training data [27], then collect the haze-free images from Google Images and Flickr and use them to create the synthetic depth maps and the equivalent hazy images for obtaining sufficient training samples. Generating the training samples is illustrated in Figure 3.…”

Section: B Training Data Collectionmentioning

confidence: 99%

Color Attenuation Prior (CAP) for Single Image Dehazing

Navale¹,

Sawant²,

Bagal³

2018

int. jour. eng. com. sci

View full text Add to dashboard Cite

Abstract:Single image haze removal has been a challenging problem due to its ill-posed nature. In this paper, we have used a simple but powerful color attenuation prior for haze removal from a single input hazy image. By creating a linear model for modeling the scene depth of the hazy image under this novel prior and learning the parameters of the model with a supervised learning method, the depth information can be well recovered. With the depth map of the hazy image, we can easily estimate the transmission and restore the scene radiance via the atmospheric scattering model, and thus effectively remove the haze from a single image. Experimental results show that the proposed approach outperforms state-of-the-art haze removal algorithms in terms of both efficiency and the dehazing effect.

show abstract

Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing

Cited by 507 publications

References 17 publications

A Fast Method for Haze Evacuation in Remote Sensing Images by Using Gaussian Filter

A Fast Method for Haze Evacuation in Remote Sensing Images by Using Gaussian Filter

Single Image Haze Removal Using Structure-Aware Atmospheric Veil

Color Attenuation Prior (CAP) for Single Image Dehazing

Contact Info

Product

Resources

About