Explore the vast range of titles available.

This paper investigates the role that virtual environments can play in assisting engineers and divers when performing subsea inspections. We outline the current state of research and technology that is relevant to the development of effective virtual environments. Three case studies are presented demonstrating how the inspection process can be enhanced through the use of virtual data. The first case study looks at how immersive virtual underwater scenes can be created to help divers and inspectors plan and implement real-world inspections. The second case study shows an example where deep learning-based computer vision methods are trained on datasets comprised of instances of virtual damage, specifically instances of barnacle fouling on the surface of a ship hull. The trained deep models are then applied to detect real-world instances of biofouling with promising results. The final case study shows how image-based damage detection methods can be calibrated using virtual images of damage captured under various simulated levels of underwater visibility. The work emphasizes the value of virtual data in creating a more efficient, safe and informed underwater inspection campaign for a wide range of built infrastructure, potentially leading to better monitoring, inspection and lifetime performance of such underwater structures.

The article presents a practical method that combines low-cost camera systems with remotely operated vehicles (ROVs) to accomplish a comprehensive but economically feasible underwater survey of large hydropower infrastructures. Typically, inspecting reservoirs entails draining them off to allow for visual inspections, which are time-intensive, pose risks to operators' safety and are associated with generation losses. In this regard, ROVs are a much safer and more efficient alternative to traditional methods. The study was conducted at the Pack reservoir in Austria, where a reference framework was set up using terrestrial laser scanning and checkerboard markings for the above-water components. A ROV equipped with a GoPro camera and lighting system for the underwater recordings has been employed. Via a close-range photogrammetric approach, it was possible to generate 3D point clouds of the submerged infrastructure with a survey-grade accuracy level. Various strategies were explored to perform bundle block adjustment (BBA), among these were strategies where ground control points (GCPs) were used, strategies without the use of GCPs but pre-calibrated initial camera parameters and strategies with a combination of using both GCPs and pre-calibrated camera parameters in the BBA. The deployment of an inspection technique using low-cost sensors that can generate highly detailed three-dimensional models of submerged infrastructure areas is presented and discussed, allowing easy detection and localization for maintenance inspection, all while being cost-effective. The paper strengthens the suggestion of best practices that optimize camera settings, considering the effect of electronic image stabilization, suggesting its avoidance, and using advanced calibration methods.

Purpose The purpose of this paper is to carry out the application of risk reliability-based underwater inspection (RReBUI). Design/methodology/approach The consequence of failure factor is calculated qualitatively in accordance with the risk-based underwater inspection (RBUI) method but the criteria are modified as an adjustment to the addition and combination of production and reliability information of the analyzed platforms. The probability of failure (PoF) is determined quantitatively by calculating the structure reliability index based on collapse failure mechanism in which the uncertainty of wave load is considered. The PoF criteria from the RBUI are re-modified to adjust the criterion with the highest and lowest reliability indexes obtained in RReBUI study. Selection of exposure category of the platform is still the same as the RBUI method. Findings The models of three offshore jacket platforms located in each of Java Sea and Natuna Sea were used for the RReBUI application. These six models were previously used in the traditional RBUI application. The results of RReBUI analysis indicated that including the environmental characteristics in the risk assessment resulted in more reliable inspection interval plans. Originality/value The drawback of RBUI is that it cannot be used for platforms spread over a distance or different areas, as the failure parameters of these platforms cannot be compared. Furthermore, the RBUI method does not consider the environmental characteristics in its risk assessment. Unlike RBUI, the purpose of RReBUI method is to assess the reliability of a platform based on both structural and environment characteristics. Therefore, the RReBUI method determines the risk of every platform quantitatively without having to compare the failure parameters based on expert justification. The application of RReBUI for jacket platforms has never been developed in Indonesia.

Due to the limitations of existing methods in identifying the diverse shapes of underwater siltation, such as branches and stones, this study proposes a rapid identification method of underwater siltation in front of the gate. Based on the YOLOv8s architecture, the model integrates FasterNet’s efficient feature extraction module, EMA’s multi-scale attention mechanism, and replaces CIoU with MPDIoU as the localization loss function, efficiently detecting underwater siltation like branches and stones. Experimental results demonstrate that the proposed model effectively distinguishes underwater siltation like branches and stones, achieving 0.821 precision, 0.513 recall, 0.627 mAP50, 0.359 mAP50-95, and an identification speed of 120.63 FPS, meeting real-time underwater inspection requirements.

It is efficient to replace human eyes with underwater vehicles equipped with visual sensors to carry out underwater inspections. However, the inability of monocular vision to provide accurate depth information highlights the importance of binocular vision in underwater target detection and measurement. In this paper, an ROV (Remotely Operated Vehicles) based binocular vision system incorporating a specially designed underwater robot is developed to carry out underwater structure detection in real-time. The system is designed to adapt to long-distance and long-duration underwater missions in various underwater environments. Taking cracks as inspection targets, a crack detection and measurement approach is proposed after the robot’s surface cleaning function is applied. Firstly, an affine transformation model is used to enhance the color-distorted underwater images effectively. Then, the multi-directional gray-level fluctuation analysis is applied to acquire an accurate crack segmented result. Finally, the computed disparity map is combined with the segmentation map to determine the crack width quickly. A group of experiments is performed and the validity and effectiveness of the system and crack measurement algorithm are demonstrated.

With the development of underwater technology, it is important to develop a wide range of autonomous and remotely operated underwater vehicles for various tasks. Depending on the problem that needs to be solved, vehicles will have different designs and dimensions, while the issues surrounding reduced costs and increasing the functionality of vehicles are relevant. This article discusses the development of inspection class experimental remotely operated vehicles (ROVs) for performing coastal underwater inspection operations, with a smaller number of thrusters, but having the same functional capabilities in terms of controllability (as vehicles with traditionally-shaped layouts). The proposed design provides controllability of the vehicle in six degrees of freedom, using six thrusters. In classical design vehicles, such controllability is usually achieved using eight thrusters. The proposed design of the ROV is described; the mathematical model, the results of modeling, and experimental tests of the developed ROVs are shown.

Posidonia oceanica meadows are a species of seagrass highly dependent on rocks for their survival and conservation. In recent years, there has been a concerning global decline in this species, emphasizing the critical need for efficient monitoring and assessment tools. While deep learning-based semantic segmentation and visual automated monitoring systems have shown promise in a variety of applications, their performance in underwater environments remains challenging due to complex water conditions and limited datasets. This paper introduces a framework that combines machine learning and computer vision techniques to enable an autonomous underwater vehicle (AUV) to inspect the boundaries of Posidonia oceanica meadows autonomously. The framework incorporates an image segmentation module using an existing Mask R-CNN model and a strategy for Posidonia oceanica meadow boundary tracking. Furthermore, a new class dedicated to rocks is introduced to enhance the existing model, aiming to contribute to a comprehensive monitoring approach and provide a deeper understanding of the intricate interactions between the meadow and its surrounding environment. The image segmentation model is validated using real underwater images, while the overall inspection framework is evaluated in a realistic simulation environment, replicating actual monitoring scenarios with real underwater images. The results demonstrate that the proposed framework enables the AUV to autonomously accomplish the main tasks of underwater inspection and segmentation of rocks. Consequently, this work holds significant potential for the conservation and protection of marine environments, providing valuable insights into the status of Posidonia oceanica meadows and supporting targeted preservation efforts.

The inspection of condition of underwater pipelines (UPs) based on autonomous underwater vehicles (AUVs) requires high accuracy of positioning while the AUV is moving along to the object being examined. Currently, acoustic, magnetometric, and visual means are used to detect and track UPs with AUVs. Compared to other methods, visual navigation can provide higher accuracy for local maneuvering at short distances to the object. According to the authors of the present article, the potential of video information for these purposes is not yet fully utilized, and, therefore, the study focused on the more efficient use of stereo images taken with an AUV’s video camera. For this, a new method has been developed to address inspection challenges, which consists in the highlighting of visible boundaries and the calculation of the UP centerline using algorithms for combined processing of 2D and 3D video data. Three techniques for initial recognition of the direction of UP upon its detection were analyzed: on the basis of a stereo-pair of images using point features of the surface; using tangent planes to the UP in one of the stereo-pair; and using the UP median planes in both images of the stereo-pair. Approaches for determining the parameters of the relative positions of the AUV and the UP during the subsequent tracking are also considered. The technology proposed can be of practical use in the development of navigation systems to be applied for UP inspection without deploying additional expensive equipment, either separately or in combination with measurements from other sensors.

In this study, we propose a method for inspecting the condition of hull surfaces using underwater images acquired from the camera of a remotely controlled underwater vehicle (ROUV). To this end, a soft voting ensemble classifier comprising six well-known convolutional neural network models was used. Using the transfer learning technique, the images of the hull surfaces were used to retrain the six models. The proposed method exhibited an accuracy of 98.13%, a precision of 98.73%, a recall of 97.50%, and an F1-score of 98.11% for the classification of the test set. Furthermore, the time taken for the classification of one image was verified to be approximately 56.25 ms, which is applicable to ROUVs that require real-time inspection.

Net inspection in fish-farm cages is a daily task for divers. This task represents a high cost for fish farms and is a high-risk activity for human operators. The total inspection surface can be more than 1500 m2, which means that this activity is time-consuming. Taking into account the severe restrictions for human operators in such hostile underwater conditions, this activity represents a significant area for improvement. A platform for net inspection is proposed in this work. This platform includes a surface vehicle, a ground control station, and an underwater vehicle (BlueROV2 heavy) which incorporates artificial intelligence, trajectory control procedures, and the necessary communications. In this platform, computer vision was integrated, involving a convolutional neural network trained to predict the distance between the net and the robot. Additionally, an object detection algorithm was developed to recognize holes in the net. Furthermore, a simulation environment was established to evaluate the inspection trajectory algorithms. Tests were also conducted to evaluate how underwater wireless communications perform in this underwater scenario. Experimental results about the hole detection, net distance estimation, and the inspection trajectories demonstrated robustness, usability, and viability of the proposed methodology. The experimental validation took place in the CIRTESU tank, which has dimensions of 12 × 8 × 5 m, at Universitat Jaume I.