What is the Space of Attenuation Coefficients in Underwater Computer Vision?

Akkaynak, Derya; Treibitz, Tali; Shlesinger, Tom; Loya, Yossi; Tamir, Raz; Iluz, David

doi:10.1109/cvpr.2017.68

Cited by 148 publications

(78 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results generated by different methods. From left to right are raw underwater images, and the results of fusion-based [31], retinex-based [33], UDCP [37], Red Channel [42], histogram prior [45], blurriness-based [46], GDCP [40] In open water, the red light first disappears because of its longest wavelength, followed by the green light and then the blue light [7]. Such selective attenuation in open water results in bluish or greenish underwater images, such as the raw underwater images in Fig.…”

Section: A Qualitative Evaluationmentioning

confidence: 99%

An Underwater Image Enhancement Benchmark Dataset and Beyond

Guo

Ren

et al. 2020

IEEE Trans. on Image Process.

1,255

672

View full text Add to dashboard Cite

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 realworld underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the stateof-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at https://li-chongyi.github.io/proj benchmark.html.

show abstract

Section: A Qualitative Evaluationmentioning

confidence: 99%

An Underwater Image Enhancement Benchmark Dataset and Beyond

Guo

Ren

et al. 2020

IEEE Trans. on Image Process.

1,255

672

View full text Add to dashboard Cite

show abstract

“…Sheinin et al [26] generalized the next best view concept of robot vision to scattering media and cooperative movable lighting for underwater navigation. Akkaynak et al [27] introduced the space of attenuation coefficients that can be used for many underwater computer vision tasks. Wang et al [28] proposed a method for feeble object detection of underwater images through logical stochastic resonance with delay loop.…”

Section: Related Workmentioning

confidence: 99%

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Pei

Huang

Zou

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

193

View full text Add to dashboard Cite

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional Neural Networks (CNN). Most of the existing works are focused on classifying very clear natural images, evidenced by the widely used image databases such as Caltech-256, PASCAL VOCs and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification. More specifically, we wonder whether image-classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image-classification performance. In this paper, we empirically study this problem for four kinds of degraded images -hazy images, underwater images, motion-blurred images and fish-eye images. For this study, we synthesize a large number of such degraded images by applying respective physical models to the clear natural images and collect a new hazy image dataset from the Internet. We expect this work can draw more interests from the community to study the classification of degraded images.

show abstract

“…However, its reach decreases exponentially with depth (Jerlov , Akkaynak et al. ). Other abiotic factors like temperature, nutrient concentrations, current flow, and sedimentation may also show strong gradients (Lesser et al.…”

Section: Introductionmentioning

confidence: 99%

“…It is a major source of energy via photosynthesis (Falkowski et al 1984), and an important proximate cue for reproduction. However, its reach decreases exponentially with depth (Jerlov 1976, Akkaynak et al 2017. Other abiotic factors like temperature, nutrient concentrations, current flow, and sedimentation may also show strong gradients (Lesser et al 2009, Kahng et al 2014).…”

Section: Introductionmentioning

confidence: 99%

Can mesophotic reefs replenish shallow reefs? Reduced coral reproductive performance casts a doubt

Shlesinger

Grinblat

Rapuano

et al. 2018

Ecology

Self Cite

View full text Add to dashboard Cite

Mesophotic coral ecosystems (i.e., deep coral reefs at 30-120 m depth) appear to be thriving while many shallow reefs in the world are declining. Amid efforts to understand and manage their decline, it was suggested that mesophotic reefs might serve as natural refuges and a possible source of propagules for the shallow reefs. However, our knowledge of how reproductive performance of corals alters with depth is sparse. Here, we present a comprehensive study of the reproductive phenology, fecundity, and abundance of seven reef-building conspecific corals in shallow and mesophotic habitats. Significant differences were found in the synchrony and timing of gametogenesis and spawning between shallow and mesophotic coral populations. Thus, mesophotic populations exhibited delayed or protracted spawning events, which led to spawning of the mesophotic colonies in large proportions at times where the shallow ones had long been depleted of reproductive material. All species investigated demonstrated a substantial reduction in fecundity and/or oocyte sizes at mesophotic depths (40-60 m). Two species (Seriatopora hystrix and Galaxea fascicularis) displayed a reduction in both fecundity and oocyte size at mesophotic depths. Turbinaria reniformis had only reduced fecundity and Acropora squarrosa and Acropora valida only reduced oocyte size. In Montipora verrucosa, reduced fecundity was found during one annual reproductive season while, in the following year, only reduced oocyte size was found. In contrast, reduced oocyte size in mesophotic populations of Acropora squarrosa was consistent along three studied years. One species, Acropora pharaonis, was found to be infertile at mesophotic depths along two studied years. This indicates that reproductive performance decreases with depth; and that although some species are capable of reproducing at mesophotic depths, their contribution to the replenishment of shallow reefs may be inconsequential. Reduced reproductive performance with depth, combined with the possible narrower tolerance to environmental factors, further suggests that mesophotic corals may in fact be more vulnerable than previously conceived. Furthermore, we posit that the observed temporal segregation in reproduction could lead to assortative mating, and this, in turn, may facilitate adaptive divergence across depth.

show abstract

What is the Space of Attenuation Coefficients in Underwater Computer Vision?

Cited by 148 publications

References 45 publications

An Underwater Image Enhancement Benchmark Dataset and Beyond

An Underwater Image Enhancement Benchmark Dataset and Beyond

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Can mesophotic reefs replenish shallow reefs? Reduced coral reproductive performance casts a doubt

Contact Info

Product

Resources

About