Underwater Images Research Articles

Denoising of Underwater Images with Regulated Autoencoders

Denoising of Underwater Images with Regulated Autoencoders

DMML: Deep Multi-Prior and Multi-Discriminator Learning for Underwater Image Enhancement

DMML: Deep Multi-Prior and Multi-Discriminator Learning for Underwater Image Enhancement

ConvFishNet: An efficient backbone for fish classification from composited underwater images

For the purpose of monitoring fish health, managing aquaculture, and comprehending marine ecology, there is a growing interest in the automatic classification of different fish species. Recent developments in machine vision-based classification methods, known for their speed and non-destructive nature, have led to the introduction of various automatic categorization approaches. Drawing inspiration from FishNet, a new architecture model named ConvFishNet has been proposed. This model incorporates large convolutional kernels and depth-wise separable convolutions to reduce the number of parameters in the model. Additionally, the PixelShuffle has been developed to enhance the upsampling information and improve fish classification performance. While maintaining precision in fish classification, the model achieves a lightweight design with only 0.83G. Compared with the FishNet model, the new model reduces parameters by 80 %. The model demonstrates a precision of 88.44 % on the WildFish dataset subset and 99.8 % on the Fish4knowledge dataset, surpassing existing methods including FishNet. This method shows promise for fish classification in challenging underwater environments, such as marine and aquaculture settings, and further investigation is planned for the future.

Characterization of Underwater Landslides in Krui Waters, Lampung-Indonesia using Shallow Seismic and Sonar Data

Abstract Krui Waters, Lampung, Indonesia, is an area that has the potential for a tsunami disaster. Local tsunamis can be caused by underwater landslides owing to ground movement and gravitational forces. Imaging underwater conditions using sonar and shallow seismic systems is an interesting research topic for geological disaster researchers. Underwater landslides are very important for disaster mitigation, especially for tsunami prediction. This research aims to identify the characteristics of underwater landslides around Krui Waters, Lampung, Indonesia, using imaging analysis methods from sonar data and a sub-bottom profiler (SBP). The underwater landslide phenomenon in this area is still not known in detail, and therefore requires further research. All data were obtained from the results of hydrographic, geological, and geophysical surveys of RV Baruna Jaya IV in 2020. The sonar data shows surface characteristics such as the presence of Furrows (Gravel Waves), Cobble (Boulder), as well as Canyons and landslides or mass movements rocks. SBP data show the characteristics of the seabed in the form of a canyon with a slope greater than 160. Finally, the morphological characteristics and features obtained could possibly be a potential source of local tsunamis owing to the high slope.

Underwater image enhancement based on global features and prior distribution guided

Underwater images often suffer from substantial image blur and color distortion due to the variability of water conditions and the physical location of optical equipment, which significantly impacts the underwater intelligent system's environmental perception. Standard methods exhibit limited generalization capabilities, leading to considerable performance fluctuations when handling images with uncontrolled degradation. In this research, we leverage global features and the prior distribution of ground truth images to guide our enhancement model, introducing a novel conditional Variational Auto-Encoder-based model, named UWG-VAE, to address these challenges. UWG-VAE enhances model controllability by incorporating prior distribution information and classes of degraded styles into the decoder of the enhancement model. We assess the performance of UWG-VAE in underwater image enhancement tasks across four challenging real underwater image datasets, comparing it to state-of-the-art models. UWG-VAE demonstrates a substantial enhancement in visual quality, with notable improvements in UIQM, UCIQE, and URanker evaluation metrics when compared to existing state-of-the-art models.

Fish Species Detection Using Deep Learning

Abstract: This research explores the application of deep learning techniques for fish species detection in underwater environments. convolutional neural networks (CNNs) trained on extensive datasets, the study aims to enhance the accuracy and efficiency of species identification. The proposed model demon- strates promising results in differentiating diverse fish species, contributing to advancements in aquatic ecology monitoring and biodiversity conservation. The integration of deep learning in fish species detection holds potential for improving our understanding of underwater ecosystems and supporting sustainable fisheries management. The relative abundance of fish pieces in their habitats on a regular basis and keeping an eye on population fluctuations, this are a crucial task for marine scientists andconservationists diverse automatic computer based fish sample methods have been demonstrated in underwater photos and videos as alternatives to time consuming hand sampling there isn’t however a perfect method for automatically detecting fish and classifying the species this is mostly due to the difficulties in producing clear underwater images and videos which include environmental fluctuations in lightning fish camouflage Dynamicbackdrops murky water low resolution shape deformations of moving fish.

A Triadic Approach for Enhancement of Underwater Images Using Adaptive Colour Correction with Unsharp Masking and CLAHE Implementation

A Triadic Approach for Enhancement of Underwater Images Using Adaptive Colour Correction with Unsharp Masking and CLAHE Implementation

RGB/Event signal fusion framework for multi-degraded underwater image enhancement

RGB/Event signal fusion framework for multi-degraded underwater image enhancement

Research on underwater robot ranging technology based on semantic segmentation and binocular vision

Based on the principle of light refraction and binocular ranging, the underwater imaging model is obtained. It provides a theoretical basis for underwater camera calibration. In order to meet the requirement of underwater vehicle to identify and distance underwater target, a new underwater vehicle distance measurement system based on semantic segmentation and binocular vision is proposed. The system uses Deeplabv3 + to identify the underwater target captured by the binocular camera and generate the target map, which is then used for binocular ranging. Compared with the binocular ranging using the original drawing, the measurement accuracy of the proposed method has not changed, the measurement speed is increased by 30%, and the error rate is controlled within 5%, which meets the needs of underwater robot operations.

A learnable full-frequency transformer dual generative adversarial network for underwater image enhancement

Underwater applications present unique challenges such as color deviation, noise, and low contrast, which can degrade image quality. Addressing these issues, we propose a novel approach called the learnable full-frequency transformer dual generative adversarial network (LFT-DGAN). Our method comprises several key innovations. Firstly, we introduce a reversible convolution-based image decomposition technique. This method effectively separates underwater image information into low-, medium-, and high-frequency domains, enabling more thorough feature extraction. Secondly, we employ image channels and spatial similarity to construct a learnable full-frequency domain transformer. This transformer facilitates interaction between different branches of information, enhancing the overall image processing capabilities. Finally, we develop a robust dual-domain discriminator capable of learning spatial and frequency domain characteristics of underwater images. Extensive experimentation demonstrates the superiority of the LFT-DGAN method over state-of-the-art techniques across multiple underwater datasets. Our approach achieves significantly improved quality and evaluation metrics, showcasing its effectiveness in addressing the challenges posed by underwater imaging. The code can be found at https://github.com/zhengshijian1993/LFT-DGAN.

Multi-scale network with attention mechanism for underwater image enhancement

Underwater images suffer from severe degradation due to the complicated environments. Though numerous approaches have been proposed, accurately correcting color bias meanwhile effectively enhancing contrast is still a difficult problem. In order to address this issue, a dedicated designed Multi-scale Network with Attention mechanism (MNA) is introduced in this work. Concretely, MNA contains four key characteristics: (a) setting more convolution layers in shallow flows, (b) letting connections from high-level to adjacent low-level stream progressively, (c) simplifying dual attention mechanism embedding it in conventional residual block, (d) exploiting channel attention module to fuse multi-scale information rather than conventional summation operation. Extensive experiments demonstrate that our MNA achieves better performance than some well-recognized technologies. Meanwhile, ablation study proves the effectiveness of each component in our MNA. In addition, extended applications demonstrate the improvement of our MNA in local feature points matching and image segmentation.

Deep Learning Based Cystoscopy Image Enhancement.

Background: Endoscopy image enhancement technology provides doctors with clearer and more detailed images for observation and diagnosis, allowing doctors to assess lesions more accurately. Unlike most other endoscopy images, cystoscopy images face more complex and diverse image degradation because of their underwater imaging characteristics. Among the various causes of image degradation, the blood haze resulting from bladder mucosal bleeding make the background blurry and unclear, severely affecting diagnostic efficiency, even leading to misjudgment. Materials and Methods: We propose a deep learning-based approach to mitigate the impact of blood haze on cystoscopy images. The approach consists of two parts as follows: a blood haze removal network and a contrast enhancement algorithm. First, we adopt Feature Fusion Attention Network (FFA-Net) and transfer learning in the field of deep learning to remove blood haze from cystoscopy images and introduce perceptual loss to constrain the network for better visual results. Second, we enhance the image contrast by remapping the gray scale of the blood haze-free image and performing weighted fusion of the processed image and the original image. Results: In the blood haze removal stage, the algorithm proposed in this article achieves an average peak signal-to-noise ratio of 29.44 decibels, which is 15% higher than state-of-the-art traditional methods. The average structural similarity and perceptual image patch similarity reach 0.9269 and 0.1146, respectively, both superior to state-of-the-art traditional methods. Besides, our method is the best in keeping color balance after removing the blood haze. In the image enhancement stage, our algorithm enhances the contrast of vessels and tissues while preserving the original colors, expanding the dynamic range of the image. Conclusion: The deep learning-based cystoscopy image enhancement method is significantly better than other traditional methods in both qualitative and quantitative evaluation. The application of artificial intelligence will provide clearer, higher contrast cystoscopy images for medical diagnosis.

Decoupled variational retinex for reconstruction and fusion of underwater shallow depth-of-field image with parallax and moving objects

Underwater imaging often suffers from poor quality due to the complex underwater environment and limitations of hardware equipment, leading to images with shallow depth of field and moving objects, which pose a challenge for information fusion of image sequences from the same underwater scene. To effectively address these problems, we propose a decoupled variational Retinex method for reconstructing and fusing underwater shallow depth of field images. Specifically, we first construct a module that adopts the decoupled variational Retinex model to adjust pixel dynamic range and luminance components, enhance non-local properties’ extraction with higher-order data constraints, and significantly improve image quality. Then, we develop a precision alignment strategy for image sequences by calculating and correcting control point deviations in the overlapping areas, achieving accurate registration of the image sequences, and effectively reconstructing scenes with parallax. Moreover, scenes with moving objects within the image sequence are reconstructed by redistributing overlapping areas. We design a novel cost function based on the neighborhood information of seams, which facilitates iterative optimization of these solved seams. This process improves the segmentation accuracy within these regions, achieving more precise scene reconstruction. Compared with state-of-the-art approaches, our method demonstrates superior performance in rectifying degraded image quality and reconstructing visually appealing images, with the resulting reconstructed images showing enhanced subjective visual quality.

Recognition method of turbine pollutant adhesion in tidal stream energy generation systems based on deep learning

In light of the extended exposure of tidal stream energy generation systems to seawater, which can lead to marine biofouling and subsequent reductions in turbine efficiency, this paper presents a deep learning-based method for the identification of pollutant adhesion. This method aims to rapidly assess the status of turbine pollutant adhesion in tidal energy generation systems. A dataset of adhesion images from tidal stream energy generation system under varying levels of pollution was obtained through underwater experiments with artificial fouling. Three different deep learning algorithms were employed to investigate the enhancement of underwater biofouling image quality. Image segmentation algorithms were used to extract and identify information related to the location and area of biofouling. The results demonstrate that the proposed deep learning-based pollutant adhesion identification method effectively recognizes the adhesion status on turbine blades, improving the accuracy of pollutant identification. This approach provides an efficient and accurate means of pollutant adhesion detection and management for the operation and maintenance of tidal stream energy generation systems, ultimately reducing operational costs.

Remote 3D Imaging and Classification of Pelagic Microorganisms with A Short‐Range Multispectral Confocal LiDAR

AbstractPlankton is essential to maintain healthy aquatic ecosystems since it influences the biological carbon pump globally. However, climate change‐induced alterations to oceanic properties threaten planktonic communities. It is therefore crucial to monitor their abundance to assess the health status of marine ecosystems. In situ optical tools unlock high‐resolution measurements of sub‐millimeter specimens, but state‐of‐the‐art underwater imaging techniques are limited to fixed and small close‐range volumes, requiring the instruments to be vertically dived. Here, a novel scanning multispectral confocal light detection and ranging (LiDAR) system for short‐range volumetric sensing in aquatic media is introduced. The system expands the inelastic confocal principle to multiple wavelength channels, allowing the acquisition of 4D point clouds combining near‐diffraction limited morphological and spectroscopic data that is used to train artificial intelligence (AI) models. Volumetric mapping and classification of microplastics is demonstrated to sort them by color and size. Furthermore, in vivo autofluorescence is resolved from a community of free‐swimming zooplankton and microalgae, and accurate spectral identification of different genera is accomplished. The deployment of this photonic platform alongside AI models overcomes the complex and subjective task of manual plankton identification and enables non‐intrusive sensing from fixed vantage points, thus constituting a unique tool for underwater environmental monitoring.

USNet: underwater image superpixel segmentation via multi-scale water-net

Underwater images commonly suffer from a variety of quality degradations, such as color casts, low contrast, blurring details, and limited visibility. Existing superpixel segmentation algorithms face challenges in achieving superior performance when directly applied to underwater images with quality degradation. In this paper, to alleviate the limitations of superpixel segmentation when applied to underwater scenes, we propose the first underwater superpixel segmentation network (USNet), specifically designed according to the intrinsic characteristics of underwater images. Considering the quality degradation, we propose a multi-scale water-net module (MWM) aimed at enhancing the quality of underwater images before superpixel segmentation. The degradation-aware attention (DA) mechanism is then created and incorporated into MWM to solve light scattering and absorption, which can decrease object visibility and cause blurred edges. By effectively directing the network to prioritize locations that exhibit a considerable decrease in quality, this method enhances the visibility of those specific areas. Additionally, we extract the deep spatial features using the coordinate attention method. Finally, these features are fused with the shallow spatial information using the dynamic spatiality embedding module to embed comprehensive spatial features. Training and testing were conducted on the SUIM dataset, the underwater change detection dataset, and UIEB dataset. Experimental results show that our method achieves the best scores in terms of achievable segmentation accuracy, undersegmentation error, and boundary recall evaluation metrics compared to other methods. Both quantitative and qualitative evaluations demonstrate that our method can handle complicated underwater scenes and outperform existing state-of-the-art segmentation methods.

DDformer: Dimension decomposition transformer with semi-supervised learning for underwater image enhancement

Vision-guided Autonomous Underwater Vehicles (AUVs) have gradually become significant tools for human exploration of the ocean. However, distorted images severely limit the visual ability, making it difficult to meet the needs of complex underwater environment perception. Fortunately, recent advancements in deep learning have led to rapid developments in underwater image enhancement. The emergence of the Transformer architecture has further enhanced the capabilities of deep learning. However, the direct application of Transformer to underwater image enhancement presents challenges in computing pixel-level global information and extracting local features. In this paper, we present a novel approach that merges dimension decomposition Transformer with semi-supervised learning for underwater image enhancement. To begin, dimension decomposition attention is proposed, which enables Transformer to compute global dependencies directly at the original scale and correct color distortions effectively. Concurrently, we employ convolutional neural networks to compensate for Transformer's limitations in extracting local features, thereby enriching details and textures. Subsequently, a multi-stage Transformer strategy is introduced to divide the network into high- and low-resolution stages for multi-scale global information extraction. It helps correct color distortions while enhancing the network's focus on regions with severe degradation. Moreover, we design a semi-supervised learning framework to reduce the reliance on paired datasets and construct a corresponding multi-scale fusion discriminator to enhance the sensitivity to input data. Experimental results demonstrate that our method outperforms state-of-the-art approaches, showcasing excellent learning and generalization capabilities on subjective perception and overall evaluation metrics. Furthermore, outstanding results highlight the significant improvements it brings to downstream visual engineering applications. The code of the proposed DDformer is available at https://github.com/ZhiGao-hfuu/DDformer.

Reinforced Res-Unet transformer for underwater image enhancement

Light propagation through water is subject to varying degrees of energy loss, causing captured images to display characteristics of color distortion, reduced contrast, and indistinct details and textures. The data-driven approach offers significant advantages over traditional algorithms, such as improved accuracy and reduced computational costs. However, challenges such as optimizing network architecture, refining coding techniques, and expanding database resources must be addressed to ensure the generation of high-quality reconstructed images across diverse tasks. In this paper, an underwater image enhancement network based on feature fusion is proposed named RUTUIE, which integrates feature fusion techniques. It leverages the strengths of both Resnet and U-shape architecture, primarily structured around a streamlined up-and-down sampling mechanism. Specifically, the U-shaped structure serves as the backbone of ResNet, equipped with two feature transformers at both the encoding and decoding ends, which are linked by a single-stage up-and-down sampling structure. This architecture is designed to minimize the omission of minor features during feature scale transformations. Furthermore, the improved Transformer encoder leverages a feature-level attention mechanism and the advantages of CNNs, endowing the network with both local and global perceptual capabilities. Then, we propose and demonstrate that embedding an adaptive feature selection module at appropriate locations can retain more learned feature representations. Moreover, the application of a previously proposed color transfer method for synthesizing underwater images and augmenting network training. Extensive experiments demonstrate that our work effectively corrects color casts, reconstructs the rich texture information in natural scenes, and improves the contrast.

Target recognition and segmentation in turbid water using data from non-turbid conditions: a unified approach and experimental validation

Semantic segmentation of targets in underwater images within turbid water environments presents significant challenges, hindered by factors such as environmental variability, difficulties in acquiring datasets, imprecise data annotation, and the poor robustness of conventional methods. This paper addresses this issue by proposing a novel joint method using deep learning to effectively perform semantic segmentation tasks in turbid environments, with the practical case of efficiently collecting polymetallic nodules in deep-sea while minimizing damage to the seabed environment. Our approach includes a novel data expansion technique and a modified U-net based model. Drawing on the underwater image formation model, we introduce noise to clear water images to simulate images captured under varying degrees of turbidity, thus providing an alternative to the required data. Furthermore, traditional U-net-based modified models have shown limitations in enhancing performance in such tasks. Based on the primary factors underlying image degradation, we propose a new model which incorporates an improved dual-channel encoder. Our method significantly advances the fine segmentation of underwater images in turbid media, and experimental validation demonstrates its effectiveness and superiority under different turbidity conditions. The study provides new technical means for deep-sea resource development, holding broad application prospects and scientific value.

A Feature-Enhanced and Adaptive Routing Framework for Fish School Detection on AUVs for Degraded Underwater Imaging Environments

A Feature-Enhanced and Adaptive Routing Framework for Fish School Detection on AUVs for Degraded Underwater Imaging Environments