Study on the Classification Performance of Underwater Sonar Image Classification Based on Convolutional Neural Networks for Detecting a Submerged Human Body

DS-SIAUG: A Self-Training Approach Using a Disrupted Student Model for Enhanced Side-Scan Sonar Image Augmentation

Side-scan sonar is a principal technique for subsea target detection, where the quantity of sonar images of seabed targets significantly influences the accuracy of intelligent target recognition. To expand the number of representative side-scan sonar target image samples, a novel augmentation method employing self-training with a Disrupted Student model is designed (DS-SIAUG). The process begins by inputting a dataset of side-scan sonar target images, followed by augmenting the samples through an adversarial network consisting of the DDPM (Denoising Diffusion Probabilistic Model) and the YOLO (You Only Look Once) detection model. Subsequently, the Disrupted Student model is used to filter out representative target images. These selected images are then reused as a new dataset to repeat the adversarial filtering process. Experimental results indicate that using the Disrupted Student model for selection achieves a target recognition accuracy comparable to manual selection, improving the accuracy of intelligent target recognition by approximately 5% over direct adversarial network augmentation.

A systematic review of robotic efficacy in coral reef monitoring techniques

Coral reefs are home to a variety of species, and their preservation is a popular study area; however, monitoring them is a significant challenge, for which the use of robots offers a promising answer. The purpose of this study is to analyze the current techniques and tools employed in coral reef monitoring, with a focus on the role of robotics and its potential in transforming this sector. Using a systematic review methodology examining peer-reviewed literature across engineering and earth sciences from the Scopus database focusing on "robotics" and "coral reef" keywords, the article is divided into three sections: coral reef monitoring, robots in coral reef monitoring, and case studies. The initial findings indicated a variety of monitoring strategies, each with its own advantages and disadvantages. Case studies have also highlighted the global application of robotics in monitoring, emphasizing the challenges and opportunities unique to each context. Robotic interventions driven by artificial intelligence and machine learning have led to a new era in coral reef monitoring. Such developments not only improve monitoring but also support the conservation and restoration of these vulnerable ecosystems. Further research is required, particularly on robotic systems for monitoring coral nurseries and maximizing coral health in both indoor and open-sea settings.

Marine Sensors: Recent Advances and Challenges

The ocean has a huge impact on our way of life; therefore, there is a need to monitor and protect its biodiversity [...].

Backward scattering suppression in an underwater LiDAR signal processing based on CEEMDAN-fast ICA algorithm

A new signal-processing method to realize blind source separation (BSS) in an underwater lidar-radar system based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and independent component analysis (ICA) is presented in this paper. The new statistical signal processing approach can recover weak target reflections from strong backward scattering clutters in turbid water, thus greatly improve the ranging accuracy. The proposed method can overcome the common problem of ICA, i.e. the number of observations must be equal to or larger than the number of sources to be separated, therefore multiple independent observations are required, which normally is realized by repeating the measurements in identical circumstances. In the new approach, the observation matrix for ICA is constructed by CEEMDAN from a single measurement. BSS can be performed on a single measurement of the mixed source signals. The CEEMDAN-ICA method avoid the uncertainty induced by the change of measurement circumstances and reduce the errors in ICA algorithm. In addition, the new approach can also improve the detection efficiency because the number of measurement is reduced. The new approach was tested in an underwater lidar-radar system. A mirror and a white Polyvinyl chloride (PVC) plate were used as target, respectively. Without using the CEEMDAN- Fast ICA, the ranging error with the mirror was 12.5 cm at 2 m distance when the attenuation coefficient of the water was 7.1 m^-1. After applying the algorithm, under the same experimental conditions, the ranging accuracy was improved to 4.33 cm. For the PVC plate, the ranging errors were 5.01 cm and 21.54 cm at 3.75 attenuation length with and without the algorithm respectively. In both cases, applying this algorithm can significantly improve the ranging accuracy.

A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance

This paper presents a comprehensive overview of current deep-learning methods for automatic object classification of underwater sonar data for shoreline surveillance, concentrating mostly on the classification of vessels from passive sonar data and the identification of objects of interest from active sonar (such as minelike objects, human figures or debris of wrecked ships). Not only is the contribution of this work to provide a systematic description of the state of the art of this field, but also to identify five main ingredients in its current development: the application of deep-learning methods using convolutional layers alone; deep-learning methods that apply biologically inspired feature-extraction filters as a preprocessing step; classification of data from frequency and time–frequency analysis; methods using machine learning to extract features from original signals; and transfer learning methods. This paper also describes some of the most important datasets cited in the literature and discusses data-augmentation techniques. The latter are used for coping with the scarcity of annotated sonar datasets from real maritime missions.

Real-Time Underwater Maritime Object Detection in Side-Scan Sonar Images Based on Transformer-YOLOv5

To overcome the shortcomings of the traditional manual detection of underwater targets in side-scan sonar (SSS) images, a real-time automatic target recognition (ATR) method is proposed in this paper. This method consists of image preprocessing, sampling, ATR by integration of the transformer module and YOLOv5s (that is, TR–YOLOv5s), and target localization. By considering the target-sparse and feature-barren characteristics of SSS images, a novel TR–YOLOv5s network and a down-sampling principle are put forward, and the attention mechanism is introduced in the method to meet the requirements of accuracy and efficiency for underwater target recognition. Experiments verified the proposed method achieved 85.6% mean average precision (mAP) and 87.8% macro-F2 score, and brought 12.5% and 10.6% gains compared with the YOLOv5s network trained from scratch, and had the real-time recognition speed of about 0.068 s per image.

Study on Active Tracking of Underwater Acoustic Target Based on Deep Convolution Neural Network

The active tracking technology of underwater acoustic targets is an important research direction in the field of underwater acoustic signal processing and sonar, and it has always been issued that draws researchers’ attention. The commonly used Kalman filter active tracking (KFAT) method is an effective tracking method, however, it is difficult to detect weak SNR signals, and it is easy to lose the target after the azimuth of different targets overlaps. This paper proposes a KFAT based on deep convolutional neural network (DCNN) method, which can effectively solve the problem of target loss. First, we use Kalman filtering to predict the azimuth and distance of the target, and then use the trained model to identify the azimuth-weighted time-frequency image to obtain the azimuth and label of the target and obtain the target distance by the time the target appears in the time-frequency image. Finally, we associate the data according to the target category, and update the target azimuth and distance information for this cycle. In this paper, two methods, KFAT and DCNN-KFAT, are simulated and tested, and the results are obtained for two cases of tracking weak signal-to-noise signals and tracking different targets with overlapping azimuths. The simulation results show that the DCNN-KFAT method can solve the problem that the KFAT method is difficult to track the target under the weak SNR and the problem that the target is easily lost when two different targets overlap in azimuth. It reduces the deviation range of the active tracking to within 200 m, which is 500~700 m less than the KFAT method.

HyAdamC: A New Adam-Based Hybrid Optimization Algorithm for Convolution Neural Networks

As the performance of devices that conduct large-scale computations has been rapidly improved, various deep learning models have been successfully utilized in various applications. Particularly, convolution neural networks (CNN) have shown remarkable performance in image processing tasks such as image classification and segmentation. Accordingly, more stable and robust optimization methods are required to effectively train them. However, the traditional optimizers used in deep learning still have unsatisfactory training performance for the models with many layers and weights. Accordingly, in this paper, we propose a new Adam-based hybrid optimization method called HyAdamC for training CNNs effectively. HyAdamC uses three new velocity control functions to adjust its search strength carefully in term of initial, short, and long-term velocities. Moreover, HyAdamC utilizes an adaptive coefficient computation method to prevent that a search direction determined by the first momentum is distorted by any outlier gradients. Then, these are combined into one hybrid method. In our experiments, HyAdamC showed not only notable test accuracies but also significantly stable and robust optimization abilities when training various CNN models. Furthermore, we also found that HyAdamC could be applied into not only image classification and image segmentation tasks.

A Universal Automatic Bottom Tracking Method of Side Scan Sonar Data Based on Semantic Segmentation

Determining the altitude of side-scan sonar (SSS) above the seabed is critical to correct the geometric distortions in the sonar images. Usually, a technology named bottom tracking is applied to estimate the distance between the sonar and the seafloor. However, the traditional methods for bottom tracking often require pre-defined thresholds and complex optimization processes, which make it difficult to achieve ideal results in complex underwater environments without manual intervention. In this paper, a universal automatic bottom tracking method is proposed based on semantic segmentation. First, the waterfall images generated from SSS backscatter sequences are labeled as water column (WC) and seabed parts, then split into specific patches to build the training dataset. Second, a symmetrical information synthesis module (SISM) is designed and added to DeepLabv3+, which not only weakens the strong echoes in the WC area, but also gives the network the capability of considering the symmetry characteristic of bottom lines, and most importantly, the independent module can be easily combined with any other neural networks. Then, the integrated network is trained with the established dataset. Third, a coarse-to-fine segmentation strategy with the well-trained model is proposed to segment the SSS waterfall images quickly and accurately. Besides, a fast bottom line search algorithm is proposed to further reduce the time consumption of bottom tracking. Finally, the proposed method is validated by the data measured with several commonly used SSSs in various underwater environments. The results show that the proposed method can achieve the bottom tracking accuracy of 1.1 pixels of mean error and 1.26 pixels of standard deviation at the speed of 2128 ping/s, and is robust to interference factors.

A Review on Deep Learning-Based Approaches for Automatic Sonar Target Recognition

Underwater acoustics has been implemented mostly in the field of sound navigation and ranging (SONAR) procedures for submarine communication, the examination of maritime assets and environment surveying, target and object recognition, and measurement and study of acoustic sources in the underwater atmosphere. With the rapid development in science and technology, the advancement in sonar systems has increased, resulting in a decrement in underwater casualties. The sonar signal processing and automatic target recognition using sonar signals or imagery is itself a challenging process. Meanwhile, highly advanced data-driven machine-learning and deep learning-based methods are being implemented for acquiring several types of information from underwater sound data. This paper reviews the recent sonar automatic target recognition, tracking, or detection works using deep learning algorithms. A thorough study of the available works is done, and the operating procedure, results, and other necessary details regarding the data acquisition process, the dataset used, and the information regarding hyper-parameters is presented in this article. This paper will be of great assistance for upcoming scholars to start their work on sonar automatic target recognition.

Multiple Object Detection Based on Clustering and Deep Learning Methods

Multiple object detection is challenging yet crucial in computer vision. In This study, owing to the negative effect of noise on multiple object detection, two clustering algorithms are used on both underwater sonar images and three-dimensional point cloud LiDAR data to study and improve the performance result. The outputs from using deep learning methods on both types of data are treated with K-Means clustering and density-based spatial clustering of applications with noise (DBSCAN) algorithms to remove outliers, detect and cluster meaningful data, and improve the result of multiple object detections. Results indicate the potential application of the proposed method in the fields of object detection, autonomous driving system, and so forth.

Seabed classification using physics-based modeling and machine learning

In this work, model-based methods are employed, along with machine learning techniques, to classify sediments in oceanic environments based on the geoacoustic properties of a two-layer seabed. Two different scenarios are investigated. First, a simple low-frequency case is set up, in which the acoustic field is modeled with normal modes. Four different hypotheses are made for seafloor sediment possibilities, and these are explored using both various machine learning techniques and a simple matched-field approach. For most noise levels, the latter has an inferior performance to the machine learning methods. Second, the high-frequency model of the scattering from a rough, two-layer seafloor is considered. Again, four different sediment possibilities are classified with machine learning. For higher accuracy, one-dimensional convolutional neural networks are employed. In both cases, the machine learning methods, both in simple and more complex formulations, lead to effective sediment characterization. The results assess the robustness to noise and model misspecification of different classifiers.

Investigations of Object Detection in Images/Videos Using Various Deep Learning Techniques and Embedded Platforms—A Comprehensive Review

In recent years there has been remarkable progress in one computer vision application area: object detection. One of the most challenging and fundamental problems in object detection is locating a specific object from the multiple objects present in a scene. Earlier traditional detection methods were used for detecting the objects with the introduction of convolutional neural networks. From 2012 onward, deep learning-based techniques were used for feature extraction, and that led to remarkable breakthroughs in this area. This paper shows a detailed survey on recent advancements and achievements in object detection using various deep learning techniques. Several topics have been included, such as Viola–Jones (VJ), histogram of oriented gradient (HOG), one-shot and two-shot detectors, benchmark datasets, evaluation metrics, speed-up techniques, and current state-of-art object detectors. Detailed discussions on some important applications in object detection areas, including pedestrian detection, crowd detection, and real-time object detection on Gpu-based embedded systems have been presented. At last, we conclude by identifying promising future directions.

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap-Deep Learning

The aryl hydrocarbon receptor (AhR) is a ligand-dependent transcription factor that senses environmental exogenous and endogenous ligands or xenobiotic chemicals. In particular, exposure of the liver to environmental metabolism-disrupting chemicals contributes to the development and propagation of steatosis and hepatotoxicity. However, the mechanisms for AhR-induced hepatotoxicity and tumor propagation in the liver remain to be revealed, due to the wide variety of AhR ligands. Recently, quantitative structure–activity relationship (QSAR) analysis using deep neural network (DNN) has shown superior performance for the prediction of chemical compounds. Therefore, this study proposes a novel QSAR analysis using deep learning (DL), called the DeepSnap–DL method, to construct prediction models of chemical activation of AhR. Compared with conventional machine learning (ML) techniques, such as the random forest, XGBoost, LightGBM, and CatBoost, the proposed method achieves high-performance prediction of AhR activation. Thus, the DeepSnap–DL method may be considered a useful tool for achieving high-throughput in silico evaluation of AhR-induced hepatotoxicity.