The Use of Saliency in Underwater Computer Vision: A Review

Reggiannini, Marco; Moroni, Davide

doi:10.3390/rs13010022

Cited by 13 publications

(8 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Salient regions of an image are any visually distinguishable and semantically meaningful region in an image. The objective of any SOD algorithm is to extract the object from the background in an image (Reggiannini and Moroni (2021)).…”

Section: Saliency Based Techniquesmentioning

confidence: 99%

Passive Visual Underwater Surveillance: A Survey

Subudhi

Kapoor

Rout

et al. 2023

Preprint

View full text Add to dashboard Cite

The objective of this article is to provide a detailed review of the state-of-the-art underwater surveillance process and the new trends of the same. Underwater surveillance has recently getting lots of attention because of its potential applications including the security of the coastal border, effective fish farming, deep-sea exploration, preservation of rare aquatic animals, etc. In the case of underwater, the light that is sensed by the camera got degraded due to many underwater phenomena such as haze, low illumination, scattering, absorption, diffraction, and refraction. The actual color of the object, as well as the scene, gets degraded as the light can not travel deep underwater. In a situation, where the scene of view is not clear, it is very difficult to detect the moving objects present in the scene. Further, the identification of the object of concern and tracking of that becomes more challenging. In this survey, we categorize underwater surveillance as a combination of the three blocks: enhancement, object detection, and object tracking. We categorize all these three blocks based on the underwater complexity and motion models considered. In this article, we tried to enumerate the most detailed descriptions of each category. We also discuss the future directions of research in the area of underwater surveillance.

show abstract

Section: Saliency Based Techniquesmentioning

confidence: 99%

Passive Visual Underwater Surveillance: A Survey

Subudhi

Kapoor

Rout

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The passive methods both rely on robust feature detection, which can be difficult to reliably achieve in real-world subsea conditions; Reggiannini and Moroni [27] highlight, in a recent review, the advantage of using machine learning for feature detection to increase the performance of feature detection in low texture underwater environments.…”

Section: Foundation Typementioning

confidence: 99%

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

Liniger

Jensen

Pedersen

et al. 2022

OCEANS 2022 - Chennai

View full text Add to dashboard Cite

“…They also compared numerous underwater image enhancement techniques in both qualitative and quantitative manner. Depends upon the principle of algorithm, the techniques on visibility improvement of underwater images are surveyed (Bharati et al, 2018;Fayaz et al, 2021;Hashisho et al, 2019;Khamparia et al, 2021;Moghimi & Mohanna, 2021;Raveendran et al, 2021;Reggiannini & Moroni, 2021;Sharma et al, 2021;Wang et al, 2019Wang et al, , 2020Zhang et al, 2019) grouped under six-classes and their sub-classes are depicted in Fig. 2.…”

Section: Related Workmentioning

confidence: 99%

Visibility improvement of underwater turbid image using hybrid restoration network with weighted filter

Muthuraman

Santhanam

2021

Multidim Syst Sign Process

View full text Add to dashboard Cite

Due to the attenuation of light passes through water, the captured underwater images suffer from low-contrast, halo artifacts, etc. To address this issue, the hybrid network with a weighted filter is proposed to improve the visibility of the obscured (turbid) images. In the captured image, the brighter pixels (near-to-source) are called foreground regions and the darker pixels (far-from-source) are called background regions. In order to ensure the adaptability of the proposed algorithm, the considered datasets are collected on different atmospheric light such as pond, lake, and fisheries tank. The foreground area of an image can be enhanced using the thresholding and masking technique. The background hazy region can be recovered by a hybrid Dehazenet called Generative Adversarial Network and Convolutional Neural Network. With this, the transmission map with high accuracy and color deviation can be addressed. Then both the regions are blended and the Amended Unsharp Mask filter is used to toughen the distorted edges. Finally, the blended restored image is weighted with a contrast factor to obtain the visibility improved image. The subjective and objective evaluation is done on considering the standard non-reference metric called Underwater Image Quality Measure comprises measures of color, sharpness, and contrast for a variety of water types with different atmospheric light. It is observed that the proposed technique showed a metric improvement of 57% compared to other existing techniques in an average manner. Overall, it is inferred that the proposed technique produces better results in both subjective and objective evaluation, thus it outperforms other state-of-the-art techniques.

show abstract

The Use of Saliency in Underwater Computer Vision: A Review

Cited by 13 publications

References 90 publications

Passive Visual Underwater Surveillance: A Survey

Passive Visual Underwater Surveillance: A Survey

On the Autonomous Inspection and Classification of Marine Growth on Subsea Structures

Visibility improvement of underwater turbid image using hybrid restoration network with weighted filter

Contact Info

Product

Resources

About