Colour image dehazing using near‐infrared fusion

Jang, Dong-Won; Park, Rae-Hong

doi:10.1049/iet-ipr.2017.0192

Cited by 26 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 shows a comparison for the ‘Mountain55’ image pair. The results proposed by Feng et al [25], and Jang and Park [30] are somewhat similar. Schaul et al 's work is seemingly better in terms of contrast with respect to colour retention.…”

Section: Resultssupporting

confidence: 66%

“…In both cases, the mountain‐top at the far end is not enhanced adequately. The method proposed by Jang and Park [30] does a pretty good job in maintaining the image contrast, the image quality is slightly better than the previous two methods. Lastly, right‐hand corner of the last row, which shows the proposed result is effectively better than the previous four results in the following ways: (A) image contrast is enhanced, but at the same time the colour of the original RGB is retained, (B) image is quite sharper as compared to the original RGB colour image, as well from the results proposed by the previous techniques and (C) the mountain top which is little bluish has become more distinct (or more blue), and the valley region is also evidently brighter.…”

Section: Resultsmentioning

confidence: 99%

“…In this section, the performance of the proposed method is compared on two fronts: (A) Comparison with existing work based on fusing colour or RGB and NIR images as described by Feng et al [25], Schaul et al [27], and Jang and Park [30] and, (B) state‐of‐the‐art single image‐based methods as described by He et al [17], Zhu et al [22], and Ancuti and Ancuti [31].…”

Section: Resultsmentioning

confidence: 99%

“…Finally, Tang et al [29] used a random forest algorithm with haze‐related features like hue disparity, dark channel, and local maximum contrast for removing the haze. Jang and Park [30] proposed a method for fusing high‐frequency components of visible and NIR spectra for generating maps to combine details of the layers. Ancuti and Ancuti [31] used a strategy for fusing two hazy images by using contrast enhancement and white balance, along with luminance, chromaticity and saliency features for the weight maps.…”

Section: Related Work and Problem Definitionmentioning

confidence: 99%

See 3 more Smart Citations

Enhancing scene perception using a multispectral fusion of visible–near‐infrared image pair

2019

View full text Add to dashboard Cite

In this study, a method for fusing of visible (or standard RGB) with near‐infrared (NIR) image pair for enhancing a hazy image is proposed. Better image enhancement in terms of contrast, sharpness, increased perception is realised by combining the components from both the spectra. While there are a number of applications that use NIR images, very few combine RGB and NIR information of the same scene taken from two separate imaging devices. Although NIR images are greyscaled in nature, they have intrinsic properties desirable in both colour and visible imagery of a number of scenes. Instances are increased the contrast between sky and clouds; shadowed and non‐shadowed regions; and increased optical depth. These features are in most cases missed by a standard RGB camera and therefore, a fusion of such RGB–NIR image pairs is highly beneficial. The scheme for fusing these image pairs is realised by using a novel, fuzzy clustering algorithm along with wavelet transform so that not only contrast and sharpness are enhanced, but also the chromaticity of the original RGB image is retained. The proposed technique is well demonstrated for various outdoor scenes, and better results are obtained when compared against some of the state‐of‐the‐art techniques proposed recently.

show abstract

Section: Resultssupporting

confidence: 66%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Related Work and Problem Definitionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing scene perception using a multispectral fusion of visible–near‐infrared image pair

2019

View full text Add to dashboard Cite

show abstract

“…In the computer vision field, multispectral images make up the data in the non-visible light spectrum and help better understand the scene characteristics. For example, Freiburg Forest dataset Apart from semantic segmentation, multi-spectral images are also used in other computer vision tasks, including pedestrian detection [152,153], face recognition [154], image dehazing [155,156], video surveillance [157], to name a few.…”

Section: Near-infrared Datasetsmentioning

confidence: 99%

Deep multimodal fusion for semantic image segmentation: A survey

Zhang

Sidibé

Morel

et al. 2021

Image and Vision Computing

129

View full text Add to dashboard Cite

Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in computer vision. In particular, we provide a systematic survey of multimodal fusion methodologies, multimodal segmentation datasets, and quantitative evaluations on the benchmark datasets. Existing fusion methods are summarized according to a common taxonomy: early fusion, late fusion, and hybrid fusion. Based on their performance, we analyze the strengths and weaknesses of different fusion strategies. Current challenges and design choices are discussed, aiming to provide the reader with a comprehensive and heuristic view of deep multimodal image segmentation.

show abstract

Enhanced machine perception by a scalable fusion of RGB–NIR image pairs in diverse exposure environments

Kumar

Singh

et al. 2021

Machine Vision and Applications

View full text Add to dashboard Cite

Colour image dehazing using near‐infrared fusion

Cited by 26 publications

References 19 publications

Enhancing scene perception using a multispectral fusion of visible–near‐infrared image pair

Enhancing scene perception using a multispectral fusion of visible–near‐infrared image pair

Deep multimodal fusion for semantic image segmentation: A survey

Enhanced machine perception by a scalable fusion of RGB–NIR image pairs in diverse exposure environments

Contact Info

Product

Resources

About