Underwater Images Research Articles

Underwater Image Enhancement Methods Using Biovision and Type-II Fuzzy Set

Accurately extracting underwater images has never been more challenging, as the lack of clarity of detail due to issues such as scattering and light absorption is more noticeable than ever before. This research method addresses these problems while clarifying the limitations of existing methods and proposes a comprehensive approach to underwater image processing. Current methods tend to focus only on the effects of individual factors, such as color shifts, visibility, or contrast enhancement, and do not take into account biological vision applications. In contrast, the method proposed in this paper applies a color correction module that takes into account the effects of biological vision in LAB color space, and an enhanced Type-II Fuzzy set visibility enhancement module. This synchronized approach overcomes the limitations of the previous methods in that the contrast enhancement utilizes a curve transform and a multi-scale fusion strategy that preserves the essential image details. The framework not only adjusts the overall image features, but also finely handles the local details, resulting in a significant enhancement of both the overall quality and the local detail clarity of underwater images. The experimental results demonstrate that the application of the method of this study on two datasets gives results that are better than those of the top 10 existing algorithms. By explicitly addressing the limitations of existing methods, the method becomes an advantageous solution in underwater image processing, providing enhancements in image quality and task-specific applications in a concise and efficient manner.

Research on multi-scale fusion image enhancement and improved YOLOv5s lightweight ROV underwater target detection method.

Underwater target detection technology is very important for Marine resources detection and underwater environment perception. The problems of low-quality underwater images, a large amount of calculation, and low accuracy of target detection models still need to be solved. Firstly, a new underwater image enhancement algorithm based on multi-scale fusion is proposed. The algorithm combines the improved white balance algorithm and the improved CLAHE (Contrast Limited Adaptive Histogram Equalization) and realizes the multi-scale fusion strategy by introducing different weight maps, aiming to improve the visual effect and quality of underwater images. Secondly, to further improve the accuracy and efficiency of underwater target detection, an improved YOLOv5s lightweight underwater target detection algorithm is proposed. The algorithm combines the Ghost convolution module, EMA(Efficient Multi-Scale Attention) mechanism, and CARAFE (Content-Aware ReAssembly of FEatures) up-sampling mode. The comparison on the URPC(Underwater Robot Perception Challenge) public dataset shows that the proposed algorithm has achieved significant improvement in terms of model size, parameter amount, calculation amount, and mAP@0.5. Thirdly, to verify the effectiveness of the image enhancement algorithm and underwater target detection algorithm proposed in this paper, the ROV(Remote Operated Vehicle) is used to conduct experiments in the experimental pool. By designing underwater target detection experiments before and after image enhancement, the results show that the enhanced image significantly improves the detection ability of underwater targets. Finally, underwater target detection software is developed to provide strong support for the application of underwater-related fields.

Controllable Ultrathin Nickel Nanoislands With Dense Discrete Space Charge Regions: Steering Hole Extraction for High-Performance Underwater Multispectral Weak-Light Photodetection.

Undersea optical communication (UOC) is vital for ocean exploration and military applications. In the dim-light underwater environment, photodetectors must maximize photon utilization by minimizing optical losses and carrier recombination. This can be achieved by integrating ultrathin metal nanostructures with photocatalysts to form Schottky junctions, which enhance charge separation and injection while mitigating metal-induced light shading. The strategic design of discrete metal nanostructures providing numerous high-depth space charge regions (SCRs) without overlap offers a promising approach to optimize hole transport paths and further suppress recombination. Here, a facile phase-separation lithography technique is explored to fabricate tunable ultrathin Ni nanoislands atop n-Si, yielding high-performance photoelectrochemical photodetectors (PEC PDs) tailored for underwater weak-light environments. This results indicate that key determinant of hole extraction behavior is the relationship between the spacing distance of adjacent Ni nanostructures (ds) and twice the SCR radius (Ws). PEC PDs with optimized 8nm ultrathin Ni nanostructures featuring closely but non-overlapping SCRs, exhibit a 55-fold increase in photoresponsivity (2.2mAW-1) and a 128-fold enhancement in detection sensitivity (3.2 × 1011 Jones) at 0V over Ni film, revealing the exceptional stability. Furthermore, this approach enables effective detection across UV-vis-near infrared spectrum, supporting reliable multispectral UOC and underwater imaging capabilities.

A Low-Cost Modulated Laser-Based Imaging System Using Square Ring Laser Illumination for Depressing Underwater Backscatter

Underwater vision data facilitate a variety of underwater operations, including underwater ecosystem monitoring, topographical mapping, mariculture, and marine resource exploration. Conventional laser-based underwater imaging systems with complex system architecture rely on high-cost laser systems with high power, and software-based methods can not enrich the physical information captured by cameras. In this manuscript, a low-cost modulated laser-based imaging system is proposed with a spot in the shape of a square ring to eliminate the overlap between the illumination light path and the imaging path, which could reduce the negative effect of backscatter on the imaging process and enhance imaging quality. The imaging system is able to achieve underwater imaging at long distance (e.g., 10 m) with turbidity in the range of 2.49 to 7.82 NTUs, and the adjustable divergence angle of the laser tubes enables the flexibility of the proposed system to image on the basis of application requirements, such as the overall view or partial detail information of targets. Compared with a conventional underwater imaging camera (DS-2XC6244F, Hikvision, Hangzhou, China), the developed system could provide better imaging performance regarding visual effects and quantitative evaluation (e.g., UCIQUE and IE). Through integration with the CycleGAN-based method, the imaging results can be further improved, with the UCIQUE increased by 0.4. The proposed low-cost imaging system with a compact system structure and low consumption of energy could be equipped with platforms, such as underwater robots and AUVs, to facilitate real-world underwater applications.

Light transport in turbid water for 3D underwater imaging

Light transport in turbid water for 3D underwater imaging

No-Reference Quality Assessment Based on Dual-Channel Convolutional Neural Network for Underwater Image Enhancement

Underwater images are important for underwater vision tasks, yet their quality often degrades during imaging, promoting the generation of Underwater Image Enhancement (UIE) algorithms. This paper proposes a Dual-Channel Convolutional Neural Network (DC-CNN)-based quality assessment method to evaluate the performance of different UIE algorithms. Specifically, inspired by the intrinsic image decomposition, the enhanced underwater image is decomposed into reflectance with color information and illumination with texture information based on the Retinex theory. Afterward, we design a DC-CNN with two branches to learn color and texture features from reflectance and illumination, respectively, reflecting the distortion characteristics of enhanced underwater images. To integrate the learned features, a feature fusion module and attention mechanism are conducted to align efficiently and reasonably with human visual perception characteristics. Finally, a quality regression module is used to establish the mapping relationship between the extracted features and quality scores. Experimental results on two public enhanced underwater image datasets (i.e., UIQE and SAUD) show that the proposed DC-CNN method outperforms a variety of the existing quality assessment methods.

A Nonconvex Approach with Structural Priors for Restoring Underwater Images

Underwater image restoration is a crucial task in various computer vision applications, including underwater target detection and recognition, autonomous underwater vehicles, underwater rescue, marine organism monitoring, and marine geological survey. Among other categories, the physics-based methods restore underwater images by improving the transmission map through optimization or regularization techniques. Conventional optimization-based methods often do not consider the effect of structural differences between guidance and transmission maps. To address this issue, in this paper, we present a regularization-based method for restoring underwater images that uses coherent structures between the guidance map and the transmission map. The proposed approach models the optimization of transmission maps through a nonconvex energy function comprising data and smoothness terms. The smoothness term includes static and dynamic structural priors, and the optimization problem is solved using a majorize-minimize algorithm. We evaluate the proposed method on benchmark datasets, and the results demonstrate the superiority of the proposed method over state-of-the-art techniques in terms of improving transmission maps and producing high-quality restored images.

A multimodal approach with firefly based CLAHE and multiscale fusion for enhancing underwater images

A multimodal approach with firefly based CLAHE and multiscale fusion for enhancing underwater images

Correction: A Two-Stage Approach for Underwater Image Enhancement Via Color-Contrast Enhancement and Trade-Off

Correction: A Two-Stage Approach for Underwater Image Enhancement Via Color-Contrast Enhancement and Trade-Off

A robust approach for balancing the color and light integrity of underwater images

Abstract As light travels under the deep water, it scatters and is absorbed, resulting in a loss of intensity and altered color perception—a phenomenon known as underwater light attenuation. Images captured under these low light conditions suffered from color distortions, as you go deeper, colors fade in this order: red, orange, and yellow, while green and blue become more prominent. The red channel experiences significant attenuation due to the scattering properties of light under the deep water. As a consequence, deep water images often display noticeable color casts. Researchers encounter various challenges when enhancing low-light underwater images, such as reduced contrast, detail loss, artifacts, noise, and color distortion. In this paper, we present a novel Adaptive Color and Light Correction (ACLC) method for color correction and an Intuitionistic Fuzzy Generator (IFG) for enhancing low-light underwater images. The proposed Adaptive Color and Light Correction (ACLC) method tackles color casts on individual pixels by considering the scene depth. The proposed Intuitionistic Fuzzy Generator (IFG) method balances the image contrast by computing an intuitionistic fuzzy image representation using the proposed IFG approach. Experimental results reveal that the proposed approach significantly improves the color quality and contrast of the output image. The proposed ACLC and IFG methods exceed existing underwater color correction and low-light image enhancement techniques in visual and quantitative evaluations, as evidenced by extensive experimentation on well-established underwater image datasets, such as UIEB, Ocean dark, and LSUI.

Effect of the estimation result of the degree of polarization of target light on clear imaging.

Previous underwater imaging methods have not developed a clear idea of estimating the degree of polarization of target light (Pobj). To address this issue, this Letter answers the question of how the estimation result of Pobj affects clear imaging. First, the theoretical derivation states that Pobj is simply a scale modulation factor of the imaging result. Second, experiments are conducted for validation, and results conform well to the derivation. Hence, the effect of the estimated Pobj on clear imaging is obtained. This parameter only influences brightness rather than contrast but may cause noise amplification as well as the unfavorable result of negative pixels. Therefore, no precise estimation is needed; pick the value near the ends of the definition domain directly and take the absolute value. Based on these, a new imaging formula is proposed, enabling the processing time to fulfill the actual dynamic imaging requirements. As far as we are concerned, the attained prior knowledge and formula could provide strong assistance for underwater polarization imaging.

Development of a method for estimating asari clam distribution by combining three-dimensional acoustic coring system and deep neural network

Developing non-contact, non-destructive monitoring methods for marine life is crucial for sustainable resource management. Recent monitoring technologies and machine learning analysis advancements have enhanced underwater image and acoustic data acquisition. Systems to obtain 3D acoustic data from beneath the seafloor are being developed; however, manual analysis of large 3D datasets is challenging. Therefore, an automatic method for analyzing benthic resource distribution is needed. This study developed a system to estimate benthic resource distribution non-destructively by combining high-precision habitat data acquisition using high-frequency ultrasonic waves and prediction models based on a 3D convolutional neural network (3D-CNN). The system estimated the distribution of asari clams (Ruditapes philippinarum) in Lake Hamana, Japan. Clam presence and count were successfully estimated in a voxel with an ROC-AUC of 0.9 and a macro-average ROC-AUC of 0.8, respectively. This system visualized clam distribution and estimated numbers, demonstrating its effectiveness for quantifying marine resources beneath the seafloor.

Breaststroke and butterfly intercycle kinematic variation according to different competitive levels with Statistical Parametric Mapping analysis

Breaststroke and butterfly are complex swimming techniques requiring refined motor skills to perform successfully, with coordinated and consistent interaction between propulsive and resistive forces being decisive when considering swimmers expertise. The current study analysed those techniques intercycle kinematic variation in two swimmers cohorts. Twenty elite and 15 national level swimmers performed one 25 m breaststroke and one 25 m butterfly sprints, with an underwater camera recording images at 120 Hz in the sagittal plane. Mean velocity, maximum and minimum velocities, stroke rate and length, intracycle velocity variation and phases relative duration were calculated for consecutive cycles (elite: five breaststroke/butterfly, national level: eight breaststroke/seven butterfly). The two highest peaks and the lower peak in between in breaststroke were also addressed. Intercycle and inter-groups analysis were performed using ANOVA, ANCOVA and Statistical Parametric Mapping. Elite and national level differed regarding breaststroke mean and maximum velocities, 1st and 2nd peaks and minimum between peaks (1.30 ± 0.02 vs 1.15 ± 0.02 m/s, 2.13 ± 0.05 vs 1.88 ± 0.06 m/s, 1.63 ± 0.05 vs 1.48 ± 0.05 m/s, 2.13 ± 0.05 vs 1.86 ± 0.05 m/s, 1.33 ± 0.04 vs 1.23 ± 0.04 m/s), and butterfly mean, maximum and minimum velocities, stroke rate and intracycle velocity variation, respectively (1.65 ± 0.01 vs 1.50 ± 0.01 m/s, 2.20 ± 0.04 vs 2.09 ± 0.04 m/s, 1.12 ± 0.04 vs 0.79 ± 0.04 m/s, (57.9 ± 0.9 vs 54.9 ± 1.0cycles/min, 18.4 ± 1.3 vs 23.7 ± 1.3 %). Elite and national level swimmers showed consistent breaststroke intercycle kinematic variation, but a butterfly mean velocity decay, with the upper limbs release and recovery, and the outsweep phases originating variability between butterfly cycles. Skill levels contrasted in technical and strategic features at sprint breaststroke and butterfly but showed similar velocity variability between consecutive swimming cycles.

Underwater Refractive Stereo Vision Measurement and Simulation Imaging Model Based on Optical Path

When light passes through air–glass and glass–water interfaces, refraction occurs, which affects the accuracy of stereo vision three-dimensional measurements of underwater targets. To eliminate the impact of refraction, we developed a refractive stereo vision measurement model based on light propagation paths, utilizing the normalized coordinate of the underwater target. This model is rigorous in theory, and easy to understand and apply. Additionally, we established an underwater simulation imaging model based on the principle that light travels the shortest time between two points. Simulation experiments conducted using this imaging model verified the performance of the underwater stereo vision measurement model. The results demonstrate that the accuracy achieved by the new measurement model is comparable to that of the stereo vision measurement model in the air and significantly higher than that of the existing refractive measurement model. This is because the light rays from the camera’s optical center to the refraction point at the air–glass interface do not always intersect. The experiments also indicate that the deviation in the refractive index of water lead to corresponding systematic errors in the measurement results. Therefore, in real underwater measurements, it is crucial to carefully calibrate the refractive index of water and maintain the validity of the calibration results.

Mitigating gradient conflicts via expert squads in multi-task learning

The foundation of multi-task learning lies in the collaboration and interaction among tasks. However, in numerous real-world scenarios, certain tasks usually necessitate distinct, specialized knowledge. The mixing of these different task-specific knowledge often results in gradient conflicts during the optimization process, posing a significant challenge in the design of effective multi-task learning systems. This study proposes a straightforward yet effective multi-task learning framework that employs groups of expert networks to decouple the learning of task-specific knowledge and mitigate such gradient conflicts. Specifically, this approach partitions the feature channels into task-specific and shared components. The task-specific subsets are processed by dedicated experts to distill specialized knowledge. The shared features are captured by a point-wise aggregation layer from the whole outputs of all experts, demonstrating superior performance in capturing inter-task interactions. By considering both task-specific knowledge and shared features, the proposed approach exhibits superior performance in multi-task learning. Extensive experiments conducted on the PASCAL-Context and NYUD-v2 datasets have demonstrated the superiority of the proposed approach compared to other state-of-the-art methods. Furthermore, a benchmark dataset for multi-task learning in underwater scenarios has been developed, encompassing object detection and underwater image enhancement tasks. Comprehensive experiments on this dataset consistently validate the effectiveness of the proposed multi-task learning strategy. The source code is available at https://github.com/chenjie04/Multi-Task-Learning-PyTorch.

Underwater image enhancement method via extreme enhancement and ultimate weakening

Underwater image enhancement method via extreme enhancement and ultimate weakening

RUDIE: Robust approach for underwater digital image enhancement

Processing underwater digital images is critical in ocean engineering, biology, and environmental studies, focusing on challenges such as poor lighting, image de-scattering, and color restoration. Due to environmental conditions on the sea floor, improving image contrast and clarity is essential for underwater navigation and obstacle avoidance. Particularly in turbid, low-visibility waters, we require robust computer vision techniques and algorithms. Over the past decade, various models for underwater image enrichment have been proposed to address quality and visibility issues under dynamic and natural lighting conditions. This research article aims to evaluate various image improvement methods and propose a robust model that improves image quality, addresses turbidity, and enhances color, ultimately improving obstacle avoidance in autonomous systems. The proposed model demonstrates high accuracy compared to traditional models. The result analysis indicates the proposed model produces images with greatly improved visibility and exceptional color accuracy. Furthermore, research can unlock new possibilities for underwater exploration, monitoring, and intervention by advancing the state-of-the-art models in this domain.

Global feature fusion generative adversarial network for underwater image enhancement

AbstractMost CNN‐based networks treat features in different channels and pixels similarly. However, the dispersion of light underwater results in uneven haze distribution throughout the images. To alleviate these problems, the global feature fusion generative adversarial network is proposed, to separate and enhance the global feature by channels and pixels simultaneously. The key novelty of our method is utilizing the attention mechanism to emphasize features in different channels and pixels in fusion block, which allocates higher weights to more important features. The network's reliability is further optimized through the incorporation of condition information to restrict the training of the network. Both qualitative and quantitative evaluations verify that the proposed method is capable of greater visual quality compared with other classic and state‐of‐the‐art methods.

Local Reference Feature Transfer (LRFT): A simple pre-processing step for image enhancement

Low-light, nighttime haze, and underwater images captured in harsh environments typically exhibit color deviations and reduced visibility due to light scattering and absorption. Additionally, we observe an almost complete loss of information in at least one color channel in these degraded images. To repair the lost information in each channel, we present an image preprocessing strategy called Local Reference Feature Transfer (LRFT), which employs the local feature to compensate for the color loss automatically. Specifically, we design a dedicated reference image by fusing the detail, salience, and uniform grayscale images of the raw image that ensures a balanced chromaticity distribution. Subsequently, we employ the local reference feature transfer strategy to migrate the local mean and variance of the reference image to the raw image to get a color-corrected image. Extensive evaluation experiments demonstrate that our proposed LRFT method has good preprocessing performance for the subsequent enhancement of images of different degradation types. The code is publicly available at: https://www.researchgate.net/publication/383528251_2024-LRFT.

Enhancing Underwater SLAM Navigation and Perception: A Comprehensive Review of Deep Learning Integration.

Underwater simultaneous localization and mapping (SLAM) is essential for effectively navigating and mapping underwater environments; however, traditional SLAM systems have limitations due to restricted vision and the constantly changing conditions of the underwater environment. This study thoroughly examined the underwater SLAM technology, particularly emphasizing the incorporation of deep learning methods to improve performance. We analyzed the advancements made in underwater SLAM algorithms. We explored the principles behind SLAM and deep learning techniques, examining how these methods tackle the specific difficulties encountered in underwater environments. The main contributions of this work are a thorough assessment of the research into the use of deep learning in underwater image processing and perception and a comparison study of standard and deep learning-based SLAM systems. This paper emphasizes specific deep learning techniques, including generative adversarial networks (GANs), convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and other advanced methods to enhance feature extraction, data fusion, scene understanding, etc. This study highlights the potential of deep learning in overcoming the constraints of traditional underwater SLAM methods, providing fresh opportunities for exploration and industrial use.