Enhancement of Low-Lighting Underwater Images Using Dark Channel Prior and Fast Guided Filters

Marques, Tunai Porto; Albu, Alexandra Branzan; Hoeberechts, Maia

doi:10.1007/978-3-030-05792-3_6

Cited by 5 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These dehazing artifacts can be mitigated by a process called transmission map refinement or by varying the size of the patch

used in the dark channel and transmission map calculations. Our proposed framework is built considering a thorough analysis on how to execute these two steps: in [ 33 ], we determined that the fast guided filter is an appropriate image filter to be used, and, in the present work, a novel systematic approach to select the best size for patch

is introduced (see Section 2.4 and Section 3.2.2 ).…”

Section: Proposed Approachmentioning

confidence: 99%

“…The most commonly used image filters in the related literature are Gaussian filters, bilateral filters [ 38 ] and guided/fast guided filters [ 34 , 35 ]. In [ 33 ], we use the NYU-Depth V2 [ 39 ] dataset, which offers pairs of haze-less images and their depth maps, to synthesize 100 new hazy images and ground truth transmission maps. The hazy images are used to calculate transmission maps, which are then filtered and compared to the ground truth references.…”

Section: Proposed Approachmentioning

confidence: 99%

“…The hazy images are used to calculate transmission maps, which are then filtered and compared to the ground truth references. The comparative experimental analysis that we reported in [ 33 ] concluded that the fast-guided filter is the most suitable for the refinement task.…”

Section: Proposed Approachmentioning

confidence: 99%

“…A novel low-lighting underwater image dataset called OceanDark , which is composed of multiple low-lighting underwater image samples captured by ONC using artificial lighting sources, was created to quantitatively and qualitatively evaluate the proposed framework (see Section 3.1 ). A preliminary version of this work was published in [ 33 ]. The theoretical aspects and results of this initial version are significantly expanded in the present article; namely, through the creation of a novel contrast-guided approach for transmission map and dark channel calculation, and the introduction of the OceanDark dataset as a basis of evaluation of our proposed method.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

2019

Self Cite

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

“…These dehazing artifacts can be mitigated by a process called transmission map refinement or by varying the size of the patch

is introduced (see Section 2.4 and Section 3.2.2 ).…”

Section: Proposed Approachmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Marques et al [9] was the first person in the world to use the image processing method to recover low-light images. This method was based on Dark Channel Prior and used guided filtering to smooth the transmission map.…”

Section: A Dark Channel Modelmentioning

confidence: 99%

Low-Light Underwater Image Enhancement for Deep-Sea Tripod

Kim

et al. 2019

IEEE Access

View full text Add to dashboard Cite

To monitor the sedimentary process and morphological evolution in the South China Sea, free-ascending deep-sea tripod (FDT) has been developed. This FDT was equipped with a deep-sea camera and landed on the sea floor at a depth of 2100 m. Although the FDT was equipped with an artificial light, the battery capacity limited the duration and intensity of light. Therefore, enhancing such low-illumination images to obtain clear visual effects is an important advancement for analyzing the geological evolution process. In this paper, an adaptive bright-color channel-based low-light underwater image-enhancement method and a denoising method are proposed to enhance such images and remove noise and artifacts. The experimental results demonstrated that the proposed method outperformed state-of-the-art methods. INDEX TERMS Image enhancement, underwater imaging, low lighting, deep-sea.

show abstract