Underwater Scenarios Research Articles

Underwater Optical Imaging: Methods, Applications and Perspectives

Underwater optical imaging is essential for exploring the underwater environment to provide information for planning and regulating underwater activities in various underwater applications, such as aquaculture farm observation, underwater topographical survey, and underwater infrastructure monitoring. Thus, there is a need to investigate the underwater imaging process and propose clear and long-range underwater optical imaging methods to fulfill the demands of academia and industry. In this manuscript, we classify the eighteen most commonly used underwater optical imaging methods into two groups regarding the imaging principle, (1) hardware and (2) software-based methods, each with an explanation of the theory, features, and applications. Furthermore, we also discuss the current challenges and future directions for improving the performance of current methods, such as improving the accuracy of underwater image formation model estimation, enlarging the underwater image dataset, proposing comprehensive underwater imaging evaluation metrics, estimating underwater depth and integrating different methods (e.g., hardware- and software-based methods for computational imaging) to promote the imaging performance not only in the laboratory but also in practical underwater scenarios.

Transformable Soft Gripper: Uniting Grasping and Suction for Amphibious Cross-Scale Objects Grasping.

Robotic grasping plays a pivotal role in real-world interactions for robots. Existing grippers often limit functionality to a single grasping mode-picking or suction. While picking handles smaller objects and suction adapts to larger ones, integrating these modes breaks scale boundaries, expanding the robot's potential in real applications. This article introduces grasping modes transformable soft gripper capable of achieving amphibious cross-scale objects grasping. Despite its compact and fully scalable design (20 mm in diameter prototype), it morphs into two configurations, gripping objects from 10% (2 mm) to over 1000% (200 mm) of its size, spanning a vast 100-fold range. To enhance its grasping efficacy, we derived theoretical analytical models for the two distinct grasping modes. Subsequently, we present a detailed illustration of the gripper's fabrication process. Experimental validation demonstrates the gripper's success in attaching or detaching everyday items and industrial products, achieving high success rates in both air and underwater scenarios. Amphibious grasping and card manipulation demonstrations underscore the practicality of this transformative soft robotics approach.

UIR-ES: An unsupervised underwater image restoration framework with equivariance and stein unbiased risk estimator

Underwater imaging faces challenges for enhancing object visibility and restoring true colors due to the absorptive and scattering characteristics of water. Underwater image restoration (UIR) seeks solutions to restore clean images from degraded ones, providing significant utility in downstream tasks. Recently, data-driven UIR has garnered much attention due to the potent expressive capabilities of deep neural networks (DNNs). These DNNs are supervised, relying on a large amount of labeled training samples. However, acquiring such data is expensive or even impossible in real-world underwater scenarios. While recent researches suggest that unsupervised learning is effective in UIR, none of these frameworks consider signal physical priors. In this work, we present a novel physics-inspired unsupervised UIR framework empowered by equivariance and unbiased estimation techniques. Specifically, equivariance stems from the invariance, inherent in natural signals to enhance data-efficient learning. Given that degraded images invariably contain noise, we propose a noise-tolerant loss for unsupervised UIR based on the Stein unbiased risk estimator to achieve an accurate estimation of the data consistency. Extensive experiments on the benchmark UIR datasets, including the UIEB and RUIE datasets, validate the superiority of the proposed method in terms of quantitative scores, visual outcomes, and generalization ability, compared to state-of-the-art counterparts. Moreover, our method demonstrates even comparable performance with the supervised model.

Underwater organisms detection algorithm based on multi‐scale perception and representation enhancement

AbstractTo address issues such as object‐background confusion and difficulties in multi‐scale object feature extraction in underwater scenarios, this article proposes an underwater organisms detection algorithm based on multi‐scale perception and representation enhancement. The key innovation of the proposed algorithm is the perception improvement of the deep learning model for underwater multi‐scale objects. First, for underwater large‐scale objects, omni‐dimensional dynamic convolution is embedded as an attention mechanism (AM) into the deep network to improve the network's sensitivity to large‐scale underwater objects. For underwater small‐scale objects, an information retention downsampling module is designed to reduce the effects of serious information loss. Then, a contextual transformer as an AM is introduced into shallow networks to strengthen the network's ability to extract features from small objects. The second innovation of the proposed algorithm is an underwater spatial pooling pyramid module which enhances the representation ability of the model. Furthermore, a lightweight decoupled head is designed to eliminate the conflict between classification and localization. The ablation experiment on the URPC dataset shows that the proposed models are effective for underwater object detection. The comparative experiments on the URPC and DUT‐USEG datasets demonstrate that the proposed algorithm achieves an advantage in detection performance compared with the mainstream detection algorithms and underwater detection algorithms.

Highly durable yarn-based strain sensor with enhanced underwater monitoring capabilities and rapid drowning detection for safety applications

Flexible strain sensors have garnered significant attention for their outstanding performance in fields such as telemedicine, motion management, and human–machine interfaces. However, in the demanding marine environments, these advanced sensors face challenges related to mechanical weakness, stability, and durability under wet conditions, which are critical for expanding their range of practical applications. In this study, a stable and durable yarn sensor was developed specifically tailored for underwater activity monitoring. This was achieved by using polydopamine to immobilize silver nanoparticles, thereby creating a highly conductive layer, followed by applying an impregnation coating to establish a hydrophobic layer. The resulting composite structure featured a micro-convex layer of silver nanoparticles, which provided a durable hydrophobic surface resistant to mechanical wear and capable of maintaining its electrical properties even under high-velocity water impacts. More significantly, a FWAS was engineered, which is activated by pre-stretching the yarn sensor using a water-soluble vinylon yarn. The FWAS automatically alters its resistance within 1.3 s upon detecting someone falling into the water, thereby sending out an accurate distress signal to the external world by transmitting Morse code signals via gesture movements. This innovation provides a straightforward and effective approach for timely rescue operations from drowning, demonstrating the versatility of yarn-based flexible strain sensors for use not only in air but also in underwater scenarios.

An underwater image enhancement method based on multi-scale layer decomposition and fusion

High-quality underwater images can intuitively reflect the most realistic underwater conditions, guiding for underwater environmental monitoring and resource exploration strongly. But when factors like light absorption affect underwater optical imaging, it has been found that poor visibility and blurred texture details occur in acquired images, posing challenges for the identification and detection of underwater targets. To obtain natural images, an enhancement algorithm is proposed based on multi-scale layer decomposition and fusion. The algorithm employs different strategies to recover image attenuation information from both local and global perspectives, generating two complementary preprocessed fusion inputs. For fusion input 1, operations are conducted in the RGB color space. Initially, the mean proportion of each color channel is used to identify the attenuated color channel. Then, a local compensation strategy is adaptively applied to restore the pixel intensity of the attenuated color channel. Finally, a statistical color correction method is used to eliminate color cast in the image. Fusion input 2 involves two processing stages. In the Lab color space, the algorithm uses the grayscale information to reduce the deviation in the mean values of channels a and b globally. The local mean information of the component L enhances detail textures. In the RGB color space, linear stretching is applied to correct color deviations. To fuse the structural features of two complementary preprocessed inputs and avoid interference between signals from different layers, the color channels of fused input image are first decomposed into muti-scale structural layers based on structural priors. Then, the image enhancement is achieved through layer-by-layer fusion of the corresponding color channels of the two inputs. By testing and analyzing with the, it was found that the proposed method can improve the clarity of attenuated images in various underwater scenarios of UIEBD and RUIE datasets effectively, enhancing image detail and texture richness, increases contrast, and achieving natural and comfortable visual quality. Compared with the quantitative metrics of 14 other algorithms, the proposed algorithm shows an average score improvement of 10.14, 90.48, and 2.06, respectively, in metrics AG (average gradient), EI (edge intensity), and NIQE (natural image quality evaluator). In the RUIE dataset, it shows an average score improvement of 10.21, 94.76, and 1.86, respectively.

FastUNet: Fast hierarchical multi-patch underwater enhancement network for industrial recirculating aquaculture

The industrialized aquaculture with recirculating water systems has gained increasing attention and rapid development in recent years. However, the existing underwater enhancement methods are time-consuming and severely hinder their online application in industrialized aquaculture due to the requirement for real-time processing. We found that their main limitations are the insufficient utilization of the hierarchical network approach and valuable prior information in underwater scenarios. To address this problem, we propose a novel architecture called FastUNet and introduce a visual enhancement benchmark dataset specifically designed for industrialized aquaculture with recirculating water systems. Surprisingly, by learning the fast multi-patch hierarchical module and employing prior constraints including color loss and homology loss, FastUNet achieves comparable or even better results than many deep learning methods. In terms of runtime, it is up to 30 times faster than current underwater enhancement methods. The processing time for images with a resolution of 5474 × 3653 is only 0.137s. The real application scenario of factory recirculating aquaculture is considered by FastUNet, and the embedding of prior information under the fast network framework is explored. In this paper, 14 state-of-the-art underwater enhancement methods are compared, and excellent results are obtained on 2 Full-reference datasets and 2 No-referenced datasets. The application test results of SIFT significant point detection, geometric rotation, edge detection, target segmentation and target detection were also presented, which strongly verified the feasibility of FastUNet in the field of factory recirculating aquaculture.

LUIE: Learnable physical model-guided underwater image enhancement with bi-directional unsupervised domain adaptation

Recently, learning-based underwater enhancement (UIE) methods have made considerable progress, significantly benefiting downstream tasks such as underwater semantic segmentation and underwater depth estimation. Most existing unsupervised UIE methods utilize the atmospheric image formation model to decompose underwater images into background color, transmission map, and scene radiance. However, they rely on simplified physical models for estimating the transmission map, over-simplifying its complex formation, which results in imprecise modeling of underwater scattering effects. Additionally, supervised UIE methods heavily depend on synthetic data or ground truth, leading to limited generalization capabilities due to the substantial domain gap presented in different underwater scenarios. To tackle these challenges, we propose a Learnable physical model-guided unsupervised domain adaptation framework for Underwater Image Enhancement, dubbed LUIE. LUIE learns to predict background light, depth, and scene radiance from an underwater image. We incorporate a learnable network to estimate the transmission map based on the predicted depth map. To minimize the inter-domain gap between synthetic and real underwater images, we introduce a bi-directional domain adaptation method that alternates the background light from each domain. Experimental results demonstrate the effectiveness of our proposed method compared to existing approaches, and high-level experiment results validate that our enhanced underwater results. Experiments in real-world settings on underwater ROVs platform with NVIDIA Jetson AGX Xavier further confirm the effectiveness and efficiency of our work.

Overview of underwater optical wireless communication positioning based on signal processing

Underwater Optical Wireless Communication (UWOC) stands as a pivotal technology in the realm of data transmission in challenging aquatic environments. Despite its importance, UWOC systems grapple with a plethora of interference issues that have the potential to severely compromise their performance. This abstract delves into the realm of anti-interference techniques in the domain of UWOC, with a particular focus on the utilization of signal processing methods. The narrative commences by underscoring the significance of UWOC systems and the vast array of applications they support, spanning diverse fields such as oceanography, environmental monitoring, and underwater exploration. This underscores the pressing need for robust solutions to mitigate the various forms of interference that can hinder effective data transmission in underwater scenarios. The article proceeds by introducing the various types of UWOC and delves into their current research status, with a specific emphasis on the ongoing evolution and emerging trends in the UWOC field. It then provides detailed insights into several prevalent UWOC positioning methods, outlining their distinct characteristics and the specific application contexts where they excel. Additionally, the article highlights the existing challenges and prospects for the future development of UWOC positioning technology, intending to offer valuable guidance to prospective researchers in this dynamic and critical area of underwater communication.

Stereo matching and 3D reconstruction with NeRF supervision for accurate weight estimation in free-swimming fish

Non-invasive methods of accurate estimation of fish weight are essential for biomass assessment, precision feeding, and effective management in aquaculture. However, the lack of large-scale stereo matching datasets and costly depth sensing equipment in underwater scenarios present significant challenges to accurately measure the size of free-swimming fish. This study introduces a novel NeRF-supervised stereo matching network for precise depth estimation and 3D reconstruction of the fish body. The state-of-the-art neural rendering methods are employed to generate stereo training data from image sequences. In this study, the residual network with deformable convolutions was proposed to extract contextual texture features, significantly enhancing disparity estimation accuracy at the edge of the fish body. Additionally, multiscale spatial features are fused using a feature pyramid network (FPN). To enhance the adaptability of disparity search, we introduce a lightweight Triplet Attention module to capture cross-dimensional dependencies prior to constructing the correlation volume. Experimental results demonstrate the effectiveness of the proposed depth estimation method, achieving an impressive result of 92.35% in the similarity metric, compared to the ground truth. Moreover, we developed a weight estimation model based on bass perimeter using instance segmentation and 3D reconstruction techniques. Notably, a robust correlation (correlation coefficient of 0.98) between fish perimeter and weight is observed, highlighting the potential application of our methods to enhance the accuracy of weight estimation for free-swimming fish.

Cooperative Communication Based Protocols for Underwater Wireless Sensors Networks: A Review.

Underwater wireless sensor networks are gaining popularity since supporting a broad range of applications, both military and civilian. Wireless acoustics is the most widespread technology adopted in underwater networks, the realization of which must face several challenges induced by channel propagation like signal attenuation, multipath and latency. In order to address such issues, the attention of researchers has recently focused on the concept of cooperative communication and networking, borrowed from terrestrial systems and to be conveniently recast in the underwater scenario. In this paper, we present a comprehensive literature review about cooperative underwater wireless sensor networks, investigating how nodes cooperation can be exploited at the different levels of the network protocol stack. Specifically, we review the diversity techniques employable at the physical layer, error and medium access control link layer protocols, and routing strategies defined at the network layer. We also provide numerical results and performance comparisons among the most widespread approaches. Finally, we present the current and future trends in cooperative underwater networks, considering the use of machine learning algorithms to efficiently manage the different aspects of nodes cooperation.

Enhancing Underwater Wireless Sensor Networks With Flexible Communication and Positioning

An innovative approach centred around underwater wireless communication and positioning in Underwater Wireless Sensor Networks, addressing limited coverage by proposing a dual-hop system combining optical fiber and wireless links. Time frame design and Code Division Multiplexing Access enhance multi-user signal transmission efficiency. Proof-of-concept experiments validate feasibility, with the introduction of the hybrid fish eye routing protocol further enhancing performance by intelligently combining fish-eye routing and traditional protocols for improved coverage and reliability. Moreover, the hybrid fish eye protocol incorporates adaptive routing algorithms that dynamically adjust to changes in underwater conditions, ensuring robustness and adaptability in challenging environments. Additionally, the hybrid fish eye protocol optimizes energy consumption by minimizing unnecessary transmissions, thereby prolonging the lifespan of underwater sensor networks. With full-duplex communication, precise positioning, and an extended transmission range, convergent system demonstrates significant potential for supporting high-capacity transmission among mobile nodes in forthcoming underwater scenarios

Enhancing Autonomous Underwater Vehicle Decision Making through Intelligent Task Planning and Behavior Tree Optimization

The expansion of underwater scenarios and missions highlights the crucial need for autonomous underwater vehicles (AUVs) to make informed decisions. Therefore, developing an efficient decision-making framework is vital to enhance productivity in executing complex tasks within tight time constraints. This paper delves into task planning and reconstruction within the AUV control decision system to enable intelligent completion of intricate underwater tasks. Behavior trees (BTs) offer a structured approach to organizing the switching structure of a hybrid dynamical system (HDS), originally introduced in the computer game programming community. In this research, an intelligent search algorithm, MCTS-QPSO (Monte Carlo tree search and quantum particle swarm optimization), is proposed to bolster the AUV’s capacity in planning complex task decision control systems. This algorithm tackles the issue of the time-consuming manual design of control systems by effectively integrating BTs. By assessing a predefined set of subtasks and actions in tandem with the complex task scenario, a reward function is formulated for MCTS to pinpoint the optimal subtree set. The QPSO algorithm is then leveraged for subtree integration, treating it as an optimal path search problem from the root node to the leaf node. This process optimizes the search subtree, thereby enhancing the robustness and security of the control architecture. To expedite search speed and algorithm convergence, this paper recommends reducing the search space by pre-grouping conditions and states within the behavior tree. The efficacy and superiority of the proposed algorithm are validated through security and timeliness evaluations of the BT, along with comparisons with other algorithms for automatic AUV decision control behavior tree design. Ultimately, the effectiveness and superiority of the proposed algorithm are corroborated through simulations on a multi-AUV complex task platform, showcasing its practical applicability and efficiency in real-world underwater scenarios.

Coverage Performance of Non-Lambertian Underwater Wireless Optical Communications for 6G Internet of Things

In medium- and short-range underwater application scenarios, thanks to the superior performance in transmission bandwidth, link latency, and security, underwater wireless optical communication (UWOC) is growing to be a promising complement to the mature underwater acoustic communication technique. In order to extend the future 6G Internet of Things (IOT) to various challenging and valuable underwater scenarios, the underwater spatial coverage and transmission performance has been actively discussed in typical seawater environments. However, almost all current works focus on underwater scenarios including light-emitting diode (LED) transmitters with well-known Lambertian optical beams and fail to characterize the scenarios adopting LED transmitters with distinctive non-Lambertian beam patterns. For addressing this limitation, in this article, the coverage performance of non-Lambertian UWOC for 6G is analyzed and illustrated. Furthermore, the switchable optical beam configuration scheme is proposed and estimated for UWOC. Numerical results illustrate that, compared with about 15.42 dB signal-to-noise ratio (SNR) fluctuation amplitude for UWOC with baseline Lambertian optical beam configuration, the corresponding SNR fluctuation amplitudes of UWOC based with two typical non-Lambertian optical beams are 8.71 dB and 24.60 dB. Furthermore, once the receiver depth is increased to 6.0 m, the SNR fluctuation amplitude for the above three UWOC coverage with distinct beam configuration could be reduced to 5.61 dB, 1.58 dB, and 10.33 dB, respectively.

Lightweight underwater image adaptive enhancement based on zero-reference parameter estimation network

Underwater images suffer from severe color attenuation and contrast reduction due to the poor and complex lighting conditions in the water. Most mainstream methods employing deep learning typically require extensive underwater paired training data, resulting in complex network structures, long training time, and high computational cost. To address this issue, a novel ZeroReference Parameter Estimation Network (Zero-UAE) model is proposed in this paper for the adaptive enhancement of underwater images. Based on the principle of light attenuation curves, an underwater adaptive curve model is designed to eliminate uneven underwater illumination and color bias. A lightweight parameter estimation network is designed to estimate dynamic parameters of underwater adaptive curve models. A tailored set of non-reference loss functions are developed for underwater scenarios to fine-tune underwater images, enhancing the network’s generalization capabilities. These functions implicitly control the learning preferences of the network and effectively solve the problems of color bias and uneven illumination in underwater images without additional datasets. The proposed method examined on three widely used real-world underwater image enhancement datasets. Experimental results demonstrate that our method performs adaptive enhancement on underwater images. Meanwhile, the proposed method yields competitive performance compared with state-of-the-art other methods. Moreover, the Zero-UAE model requires only 17K parameters, minimizing the hardware requirements for underwater detection tasks. What’more, the adaptive enhancement capability of the Zero-UAE model offers a new solution for processing images under extreme underwater conditions, thus contributing to the advancement of underwater autonomous monitoring and ocean exploration technologies.

UOWC Integration with ROVs: A Fiber-Optic Approach for Enhanced Underwater Exploration

Underwater Optical Wireless Communication (UOWC) revolutionizes underwater exploration, leveraging seawater's unique property—reduced absorption of blue-green light. This offers superior advantages over traditional communication methods, providing higher bandwidth and lower latency. This paper explores the integration of UOWC with Remotely Operated Vehicles (ROVs), enhancing data exchange and command capabilities in challenging underwater environments. Seawater's unique properties empower UOWC to outperform acoustic and RF methods, crucial for real-time applications. The study utilizes advanced techniques like Fiber-Optic Communication, High Order Sliding Mode Control, and Hybrid Blockage Detection for ROV integration and control. While the abstract focuses on theory and design, it sets the stage for empirical validations, emphasizing the need for future research to quantify improvements in real-world underwater scenarios

High strength and anti‐swelling hydrogel strain sensors based on amphiphilic polyurethane assemblies for human‐motion detection

AbstractHydrogel sensors are widely used in electronic skin, soft robotics, bioengineering, and medical therapy due to their excellent electrical conductivity, mechanical flexibility, and better biocompatibility. However, the swelling property of hydrogels has been hindering their application in underwater scenarios. Therefore, in this study, to address the anti‐swelling behavior of hydrogels, MXene nanosheets were modified by 1H,1H,2H,2H‐perfluorooctyltrimethoxysilane and then compounded with acrylamide and polyurethane to obtain multifunctional conductive hydrogels (PAM‐WPU/FMX hydrogels). Through the synergistic effect of chemical cross‐linking and hydrogen bonding on the gel network, the hydrogel sensor was characterized by strong resistance to swelling (swelling ratio = 2.22), excellent mechanical properties (strain at break after swelling equilibrium = 418.6%), and high strain sensitivity. For underwater applications, this study offers a model technique for the quick gelation of strong, swelling‐resistant hydrogels.Highlights Amphiphilic polyurethane micelles provided energy dissipation. Modified MXene was hydrophobic and electrically conductive. The strain of the hydrogel obtained after MXene modification was enhanced. The structural recovery capacity of both hydrogels was more than 60%. The modified hydrogel swollen but still had excellent sensing properties.

Secrecy Analysis of Decode-and-Forward Relay Based Heterogeneous Terrestrial RF - Underwater Acoustic System

This study examines how well a heterogeneous dual-hop terrestrial radio frequency and underwater acoustic downlink system maintain confidentiality. It includes an RF source, an intermediate decode-and-forward relay, an underwater multi-hydrophone destination, and a nearby eavesdropper. Eavesdropper overhears underwater acoustic signal transmitted by the relay. RF and underwater acoustic links undergo Nakagami-m and Rayleigh fading, respectively. Due to the propagation delay of underwater scenario, both destination and eavesdropper links are associated with outdated channel state information which also employs maximal-ratio combining. The closed form expressions of secrecy outage probability, strictly positive secrecy capacity, and intercept probability are derived. Monte-Carlo simulations are obtained to certify the analytical expressions.

Underwater object detection method based on learnable query recall mechanism and lightweight adapter.

With the rapid development of ocean observation technology, underwater object detection has begun to occupy an essential position in the fields of aquaculture, environmental monitoring, marine science, etc. However, due to the problems unique to underwater images such as severe noise, blurred objects, and multi-scale, deep learning-based target detection algorithms lack sufficient capabilities to cope with these challenges. To address these issues, we improve DETR to make it well suited for underwater scenarios. First, a simple and effective learnable query recall mechanism is proposed to mitigate the effect of noise and can significantly improve the detection performance of the object. Second, for underwater small and irregular object detection, a lightweight adapter is designed to provide multi-scale features for the encoding and decoding stages. Third, the regression mechanism of the bounding box is optimized using the combination loss of smooth L1 and CIoU. Finally, we validate the designed network against other state-of-the-art methods on the RUOD dataset. The experimental results show that the proposed method is effective.

Underwater Degraded Image Restoration by Joint Evaluation and Polarization Partition Fusion

Images of underwater environments suffer from contrast degradation, reduced clarity, and information attenuation. The traditional method is the global estimate of polarization. However, targets in water often have complex polarization properties. For low polarization regions, since the polarization is similar to the polarization of background, it is difficult to distinguish between target and non-targeted regions when using traditional methods. Therefore, this paper proposes a joint evaluation and partition fusion method. First, we use histogram stretching methods for preprocessing two polarized orthogonal images, which increases the image contrast and enhances the image detail information. Then, the target is partitioned according to the values of each pixel point of the polarization image, and the low and high polarization target regions are extracted based on polarization values. To address the practical problem, the low polarization region is recovered using the polarization difference method, and the high polarization region is recovered using the joint estimation of multiple optimization metrics. Finally, the low polarization and the high polarization regions are fused. Subjectively, the experimental results as a whole have been fully restored, and the information has been retained completely. Our method can fully recover the low polarization region, effectively remove the scattering effect and increase an image’s contrast. Objectively, the results of the experimental evaluation indexes, EME, Entropy, and Contrast, show that our method performs significantly better than the other methods, which confirms the feasibility of this paper’s algorithm for application in specific underwater scenarios.