Editorial

2 pages, 175 KiB

Open AccessEditorial

Advances in Autonomous Underwater Robotics Based on Machine Learning

by Antoni Burguera and Francisco Bonin-Font

J. Mar. Sci. Eng. 2022, 10(10), 1481; https://doi.org/10.3390/jmse10101481 - 12 Oct 2022

Viewed by 1270

Autonomous or semi-autonomous robots are nowadays used in a wide variety of scenarios, including marine and underwater environments [...] Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

Research

Jump to: Editorial, Review

19 pages, 9861 KiB

Open AccessArticle

Virtual Underwater Datasets for Autonomous Inspections

by Ioannis Polymenis, Maryam Haroutunian, Rose Norman and David Trodden

J. Mar. Sci. Eng. 2022, 10(9), 1289; https://doi.org/10.3390/jmse10091289 - 13 Sep 2022

Cited by 1 | Viewed by 2802

Abstract

Underwater Vehicles have become more sophisticated, driven by the off-shore sector and the scientific community’s rapid advancements in underwater operations. Notably, many underwater tasks, including the assessment of subsea infrastructure, are performed with the assistance of Autonomous Underwater Vehicles (AUVs). There have been [...] Read more.

Underwater Vehicles have become more sophisticated, driven by the off-shore sector and the scientific community’s rapid advancements in underwater operations. Notably, many underwater tasks, including the assessment of subsea infrastructure, are performed with the assistance of Autonomous Underwater Vehicles (AUVs). There have been recent breakthroughs in Artificial Intelligence (AI) and, notably, Deep Learning (DL) models and applications, which have widespread usage in a variety of fields, including aerial unmanned vehicles, autonomous car navigation, and other applications. However, they are not as prevalent in underwater applications due to the difficulty of obtaining underwater datasets for a specific application. In this sense, the current study utilises recent advancements in the area of DL to construct a bespoke dataset generated from photographs of items captured in a laboratory environment. Generative Adversarial Networks (GANs) were utilised to translate the laboratory object dataset into the underwater domain by combining the collected images with photographs containing the underwater environment. The findings demonstrated the feasibility of creating such a dataset, since the resulting images closely resembled the real underwater environment when compared with real-world underwater ship hull images. Therefore, the artificial datasets of the underwater environment can overcome the difficulties arising from the limited access to real-world underwater images and are used to enhance underwater operations through underwater object image classification and detection. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

19 pages, 7217 KiB

Open AccessArticle

YOLO-Submarine Cable: An Improved YOLO-V3 Network for Object Detection on Submarine Cable Images

by Yue Li, Xueting Zhang and Zhangyi Shen

J. Mar. Sci. Eng. 2022, 10(8), 1143; https://doi.org/10.3390/jmse10081143 - 18 Aug 2022

Cited by 14 | Viewed by 2731

Abstract

Due to the strain on land resources, marine energy development is expanding, in which the submarine cable occupies an important position. Therefore, periodic inspections of submarine cables are required. Submarine cable inspection is typically performed using underwater vehicles equipped with cameras. However, the [...] Read more.

Due to the strain on land resources, marine energy development is expanding, in which the submarine cable occupies an important position. Therefore, periodic inspections of submarine cables are required. Submarine cable inspection is typically performed using underwater vehicles equipped with cameras. However, the motion of the underwater vehicle body, the dim light underwater, and the property of light propagation in water lead to problems such as the blurring of submarine cable images, the lack of information on the position and characteristics of the submarine cable, and the blue–green color of the images. Furthermore, the submarine cable occupies a significant portion of the image as a linear entity. In this paper, we propose an improved YOLO-SC (YOLO-Submarine Cable) detection method based on the YOLO-V3 algorithm, build a testing environment for submarine cables, and create a submarine cable image dataset. The YOLO-SC network adds skip connections to feature extraction to make the position information of submarine cables more accurate, a top-down downsampling structure in multi-scale special fusion to reduce the network computation and broaden the network perceptual field, and lightweight processing in the prediction network to accelerate the network detection. Under laboratory conditions, we illustrate the effectiveness of these modifications through ablation studies. Compared to other algorithms, the average detection accuracy of the YOLO-SC model is increased by up to 4.2%, and the average detection speed is decreased by up to 1.616 s. The experiments demonstrate that the YOLO-SC model proposed in this paper has a positive impact on the detection of submarine cables. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

10 pages, 9810 KiB

Open AccessArticle

An Automated Framework Based on Deep Learning for Shark Recognition

by Nhat Anh Le, Jucheol Moon, Christopher G. Lowe, Hyun-Il Kim and Sang-Il Choi

J. Mar. Sci. Eng. 2022, 10(7), 942; https://doi.org/10.3390/jmse10070942 - 09 Jul 2022

Cited by 4 | Viewed by 2355

Abstract

The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is [...] Read more.

The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to identify images of known objects only. However, such approaches are not scalable because they mis-classify images of unknown objects. To recognize the images of unknown objects as ‘unknown’, a framework should be able to deal with the open set recognition scenario. This paper proposes a fully automatic, vision-based identification framework capable of recognizing shark individuals including those that are unknown. The framework first detects and extracts the shark from the original image. After that, we develop a deep network to transform the extracted image to an embedding vector in latent space. The proposed network consists of the Visual Geometry Group-UNet (VGG-UNet) and a modified Visual Geometry Group-16 (VGG-16) network. The VGG-UNet is utilized to detect shark bodies, and the modified VGG-16 is used to learn embeddings of shark individuals. For the recognition task, our framework learns a decision boundary using a one-class support vector machine (OSVM) for each shark included in the training phase using a few embedding vectors belonging to them, then it determines whether a new shark image is recognized as belonging to a known shark individual. Our proposed network can recognize shark individuals with high accuracy and can effectively deal with the open set recognition problem with shark images. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

23 pages, 2026 KiB

Open AccessArticle

Sim-to-Real: Mapless Navigation for USVs Using Deep Reinforcement Learning

by Ning Wang, Yabiao Wang, Yuming Zhao, Yong Wang and Zhigang Li

J. Mar. Sci. Eng. 2022, 10(7), 895; https://doi.org/10.3390/jmse10070895 - 28 Jun 2022

Cited by 7 | Viewed by 2050

Abstract

In recent years, mapless navigation using deep reinforcement learning algorithms has shown significant advantages in improving robot motion planning capabilities. However, the majority of past works have focused on aerial and ground robotics, with very little attention being paid to unmanned surface vehicle [...] Read more.

In recent years, mapless navigation using deep reinforcement learning algorithms has shown significant advantages in improving robot motion planning capabilities. However, the majority of past works have focused on aerial and ground robotics, with very little attention being paid to unmanned surface vehicle (USV) navigation and ultimate deployment on real platforms. In response, this paper proposes a mapless navigation method based on deep reinforcement learning for USVs. Specifically, we carefully design the observation space, action space, reward function, and neural network for a navigation policy that allows the USV to reach the destination collision-free when equipped with only local sensors. Aiming at the sim-to-real transfer and slow convergence of deep reinforcement learning, this paper proposes a dynamics-free training and consistency strategy and designs domain randomization and adaptive curriculum learning. The method was evaluated using a range of tests applied to simulated and physical environments and was proven to work effectively in a real navigation environment. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

31 pages, 4607 KiB

Open AccessArticle

Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM

by Antoni Burguera, Francisco Bonin-Font, Eric Guerrero Font and Antoni Martorell Torres

J. Mar. Sci. Eng. 2022, 10(4), 511; https://doi.org/10.3390/jmse10040511 - 06 Apr 2022

Cited by 9 | Viewed by 2050

Abstract

Visual Loop Detection (VLD) is a core component of any Visual Simultaneous Localization and Mapping (SLAM) system, and its goal is to determine if the robot has returned to a previously visited region by comparing images obtained at different time steps. This paper [...] Read more.

Visual Loop Detection (VLD) is a core component of any Visual Simultaneous Localization and Mapping (SLAM) system, and its goal is to determine if the robot has returned to a previously visited region by comparing images obtained at different time steps. This paper presents a new approach to visual Graph-SLAM for underwater robots that goes one step forward the current techniques. The proposal, which centers its attention on designing a robust VLD algorithm aimed at reducing the amount of false loops that enter into the pose graph optimizer, operates in three steps. In the first step, an easily trainable Neural Network performs a fast selection of image pairs that are likely to close loops. The second step carefully confirms or rejects these candidate loops by means of a robust image matcher. During the third step, all the loops accepted in the second step are subject to a geometric consistency verification process, being rejected those that do not fit with it. The accepted loops are then used to feed a Graph-SLAM algorithm. The advantages of this approach are twofold. First, the robustness in front of wrong loop detection. Second, the computational efficiency since each step operates only on the loops accepted in the previous one. This makes online usage of this VLD algorithm possible. Results of experiments with semi-synthetic data and real data obtained with an autonomous robot in several marine resorts of the Balearic Islands, support the validity and suitability of the approach to be applied in further field campaigns. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

19 pages, 18600 KiB

Open AccessArticle

Underwater Target Detection Algorithm Based on Improved YOLOv5

by Fei Lei, Feifei Tang and Shuhan Li

J. Mar. Sci. Eng. 2022, 10(3), 310; https://doi.org/10.3390/jmse10030310 - 22 Feb 2022

Cited by 65 | Viewed by 7715

Abstract

Underwater target detection plays an important role in ocean exploration, to which the improvement of relevant technology is of much practical significance. Although existing target detection algorithms have achieved excellent performance on land, they often fail to achieve satisfactory outcome of detection when [...] Read more.

Underwater target detection plays an important role in ocean exploration, to which the improvement of relevant technology is of much practical significance. Although existing target detection algorithms have achieved excellent performance on land, they often fail to achieve satisfactory outcome of detection when in the underwater environment. In this paper, one of the most advanced target detection algorithms, YOLOv5 (You Only Look Once), was first applied in the underwater environment before being improved by combining it with some methods characteristic of the underwater environment. To be specific, the Swin Transformer was treated as the basic backbone network of YOLOv5, which makes the network suitable for those underwater images with blurred targets. It is possible for the network to focus on fusing the relatively important resolution features by improving the method of path aggregation network (PANet) for multi-scale feature fusion. The confidence loss function was improved on the basis of different detection layers, with the network biased to learn high-quality positive anchor boxes and make the network more capable of detecting the target. As suggested by the experimental results, the improved network model is effective in detecting underwater targets, with the mean average precision (mAP) reaching 87.2%, which makes it advantageous over general target detection models and fit for use in the complex underwater environment. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

19 pages, 7471 KiB

Open AccessArticle

Complete Coverage Path Planning of an Unmanned Surface Vehicle Based on a Complete Coverage Neural Network Algorithm

by Peng-Fei Xu, Yan-Xu Ding and Jia-Cheng Luo

J. Mar. Sci. Eng. 2021, 9(11), 1163; https://doi.org/10.3390/jmse9111163 - 22 Oct 2021

Cited by 22 | Viewed by 2752

Abstract

In practical applications, an unmanned surface vehicle (USV) generally employs a task of complete coverage path planning for exploration in a target area of interest. The biological inspired neural network (BINN) algorithm has been extensively employed in path planning of mobile robots, recently. [...] Read more.

In practical applications, an unmanned surface vehicle (USV) generally employs a task of complete coverage path planning for exploration in a target area of interest. The biological inspired neural network (BINN) algorithm has been extensively employed in path planning of mobile robots, recently. In this paper, a complete coverage neural network (CCNN) algorithm for the path planning of a USV is proposed for the first time. By simplifying the calculation process of the neural activity, the CCNN algorithm can significantly reduce calculation time. To improve coverage efficiency and make the path more regular, the optimal next position decision formula combined with the covering direction term is established. The CCNN algorithm has increased moving directions of the path in grid maps, which in turn has further reduced turning-angles and makes the path smoother. Besides, an improved A* algorithm that can effectively decrease path turns is presented to escape the deadlock. Simulations are carried out in different environments in this work. The results show that the coverage path generated by the CCNN algorithm has less turning-angle accumulation, deadlocks, and calculation time. In addition, the CCNN algorithm is capable to maintain the covering direction and adapt to complex environments, while effectively escapes deadlocks. It is applicable for USVs to perform multiple engineering missions. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

35 pages, 4524 KiB

Open AccessReview

An Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning

by Kai Hu, Chenghang Weng, Yanwen Zhang, Junlan Jin and Qingfeng Xia

J. Mar. Sci. Eng. 2022, 10(2), 241; https://doi.org/10.3390/jmse10020241 - 10 Feb 2022

Cited by 51 | Viewed by 7773

Abstract

Underwater video images, as the primary carriers of underwater information, play a vital role in human exploration and development of the ocean. Due to the optical characteristics of water bodies, underwater video images generally have problems such as color bias and unclear image [...] Read more.

Underwater video images, as the primary carriers of underwater information, play a vital role in human exploration and development of the ocean. Due to the optical characteristics of water bodies, underwater video images generally have problems such as color bias and unclear image quality, and image quality degradation is severe. Degenerated images have adverse effects on the visual tasks of underwater vehicles, such as recognition and detection. Therefore, it is vital to obtain high-quality underwater video images. Firstly, this paper analyzes the imaging principle of underwater images and the reasons for their decline in quality and briefly classifies various existing methods. Secondly, it focuses on the current popular deep learning technology in underwater image enhancement, and the underwater video enhancement technologies are also mentioned. It also introduces some standard underwater data sets, common video image evaluation indexes and underwater image specific indexes. Finally, this paper discusses possible future developments in this area. Full article

(This article belongs to the Special Issue Advances in Autonomous Underwater Robotics Based on Machine Learning)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Autonomous Underwater Robotics Based on Machine Learning

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI