Underwater Reverberation Suppression via Attention and Cepstrum Analysis-Guided Network

Underwater target detection is an indispensable part of marine environmental engineering and a fast and accurate method of detecting underwater targets is essential. Although many target detection algorithms have achieved great accuracy in daily scenes, there are issues of low-quality images due to the complex underwater environment, which makes applying these deep learning algorithms directly to process underwater target detection tasks difficult. In this paper, we presented an algorithm for underwater target detection based on improved You Only Look Once (YOLO) v4 in response to the underwater environment. First, we developed a new convolution module and network structure. Second, a new intersection over union loss was defined to substitute the original loss function. Finally, we integrated some other useful strategies to achieve more improvement, such as adding one more prediction head to detect targets of varying sizes, integrating the channel attention into the network, utilizing K-means++ to cluster anchor box, and utilizing different activation functions. The experimental results indicate that, in comparison with YOLOv4, our proposed algorithm improved the average accuracy of the underwater dataset detection by 10.9%, achieving 91.1%, with a detection speed of 58.1 frames per second. Therefore, compared to other mainstream target detection algorithms, it is superior and feasible for applications in intricate underwater environments.

Objective: We propose a deep-learning-based underwater target detection system that can effectively solve the problem of underwater optical image target detection and recognition. Methods: In this paper, based on the depth of the underwater optical image target detection and recognition and using a learning model, we put forward corresponding solutions using the concept of style migration solutions, such as training samples. A lack of variability and poor generalization of practical applications presents a challenge for underwater object identification. The UW_YOLOv3 lightweight model was proposed to solve the problems of calculating energy consumption and storage resource limitations in underwater application scenarios. The detection and recognition module, based on deep learning, can deal with the degradation process of underwater imaging by embedding an image enhancement module into the detection and recognition module for the joint tuning and transferring of knowledge. Results: The detection accuracy of the UW_YOLOv3 model designed in this paper outperformed the lightweight algorithm YOLOV3-TINY by 7.9% at the same image scale input. Compared with other large algorithms, the detection accuracy was lower, but the detection speed was much higher. Compared with the SSD algorithm, the detection accuracy was only 4.7 lower; the speed was 40.9 FPS higher; and the rate was nearly 16 times higher than Faster R-CNN. When the input scale was 224, although part of the accuracy was lost, the detection speed doubled, reaching 156.9 FPS. Conclusion: Based on our framework, the problem of underwater optical image target detection and recognition can be effectively solved. Relevant studies have not only enriched the theory of target detection and glory, but have also provided optical glasses with a clear vision for appropriate underwater application systems.

Target of underwater environments classification and distinguish using active sonar is very complex signal processing work, therefore, many research institutions in the world study the classification and recognition methods of underwater small targets using active sonar.The recognition methods of static underwater small targets can be roughly divided into imaging method and echo method. The imaging method is based on high-frequency narrow beam to obtain the acoustic image of the target and its shadow while suppressing the reverberation interference, so as to realize the classification and recognition of the target. Imaging sonar has high working frequency, limited sonar range, and can not effectively identify false targets with similar geometry. Bright spot model and resonance scattering theory are important theoretical basis of target echo method. The two theories agree that the echo is the result of the interaction between the incident signal and the underwater target, which must contain the characteristics of the target, so it is feasible to detect the target by analyzing the characteristics of the echo signal. However, in the actual underwater target detection process, due to the weak target echo signal, complex seabed environment and target geometry, uncertain sound propagation conditions and so on, the target recognition based on echo method still has great challenges.

For the detection of shallow underwater targets by the hyperspectrum, the information of the target is carried in the water-leaving radiation. However, the differences between the water-leaving radiation of the underwater target and the ocean background radiation are not significant, and the spectrum of the water-leaving radiation is sensitive to the changes of the marine environment. Therefore, taking the spectrum as the feature is not stable for hyperspectral detection of the underwater target. In this paper, we propose a parameter feature extraction method for hyperspectral detection of the shallow underwater target. The presence of an underwater target would change the optical properties of seawater in a local place. Based on that, a quasi-analytical model of the water-leaving radiation is adopted to inverse the properties of the marine environment from the radiated spectrum. Then the inversed water depth and bottom reference reflectance are taken as the features. Simulation results show that the samples which belong to the water-leaving radiation of underwater target have higher inversed depth and reference reflectance than that belong to the ocean background radiation. Furthermore, these two kinds of samples can be separated significantly and stably in a 2-dimension feature space.

In view of the problem of difficult feature extraction and target missed detection, propose an improved transformer based underwater target detection algorithm. The proposed algorithm improves the linear embedding module of the Transformer to supplement the linear embedding information of small objects and builds the local relationship model of each layer feeling field, in order to achieve end-to-end accurate detection. An experiment on URPU underwater target detection data set is conducted. Compared with Swim Transformer, the proposed algorithm detection accuracy is 77.4%, 1. 5%, detection speed is 7 frame/s, 35.6%, the number is 30.4 MB, and compression is 84.1%. Experimental results have shown that the improved algorithm improves the performance of underwater small target detection

The detection and recognition of underwater preset structure is an important topic in the detection of potential safety hazards in underwater engineering. At present, the detection of underwater preset structure is mainly based on multi-beam sounding technology. In this paper, the submarine pipeline is taken as the research object, and a new detection method based on 3D real-time imaging sonar technology is proposed, which realizes the underwater environment acoustic high-precision real-time target detection and fine target analysis. First of all, the underwater target detection data is obtained by using 3D imaging sonar, high-precision integrated navigation, tide gauge, CTD and other equipment. Secondly, the attitude correction, sound velocity correction and depth compensation of 3D imaging data is carried out, and the bilateral filtering combined with threshold filtering is used to filter the data. Finally, combined with advanced point cloud data processing algorithms and edge data extraction based on eigenvalues, accurate identification, positioning and status analysis of submarine pipelines are achieved. The results of practical engineering detection show that this method has the advantages of high resolution, real-time imaging and excellent imaging quality. The detection image is stereoscopic and clear, which can provide more detailed description of underwater target contour. The data processing and analysis method adopted in this paper can track and identify the submarine pipeline quickly and accurately, and detect the areas with potential safety hazards such as exposed or suspended pipelines, which provides scientific basis for the timely management of pipelines. This paper provides a new detection method for submarine pipeline detection, which has applicability and popularizing value.

Aiming at the issue that in view of the common underwater target electric field detection and localization technology, its electric signal attenuation in the water is faster and easy to be affected by the underwater complex environmental noise, which affects the detection performance of the problem, the paper carries out a research based on active and passive electric field detection and localization technology. First, a target electric field detection and localization system is designed. Then, two sets of basis functions in the horizontal and vertical directions are derived based on this detection system model, and then the detection and localization of underwater targets are realized by energy calculation. Finally, the image fusion algorithm of wavelet transform is adopted to further realize the detection and localization of underwater targets in a two-dimensional plane through the form of a heatmap. All the above contents are experimentally verified by simulation tools, and the experimental results show that compared with the traditional electric field detection and localization techniques for underwater targets, the method in this paper has better performance in the environment with a lower signal-to-noise ratio.

With the increasingly extensive use of diver and unmanned underwater vehicle in military, it has posed a serious threat to the security of the national coastal area. In order to prevent the underwater diver's impact on the safety of water area, it is of great significance to identify underwater small targets in time to make early warning for it. In this paper, convolutional neural network is applied to underwater small target recognition. The recognition targets are diver, whale and dolphin. Due to the time-frequency spectrum can reflect the essential features of underwater target, convolutional neural network can learn a variety of features of the acoustic signal through the image processed by the time-frequency spectrum, time-frequency image is input to convolutional neural network to recognize the underwater small targets. According to the study of learning rate and pooling mode, the network parameters and structure suitable for underwater small target recognition in this paper are selected. The results of data processing show that the method can identify underwater small targets accurately.

CMRE is evaluating the use of autonomous robots for the detection and tracking of underwater targets. Robotic detection and localization comes with many challenges, not the least of which is the requirement to maximize the probability of detection of targets while minimizing the rate of false alarm. In order to do this, underwater robots performing detection and localization will require some form of on board decision engine to guide their trajectories while performing their missions. Many of the autonomy frameworks for determining these trajectories being developed at CMRE are based on a comprehensive model for multistatic active performance called the Multi-Static Tactical Planning Aid, which predicts how the probability of detection of underwater targets varies in complex environments with range dependent sound speed profile and bathymetry. However, there are residual parameters of the model, such as bottom scattering strength and bottom loss, which must be tuned in order for MSTPA to provide predictions which are in accordance with the actual sonar performance being observed by the robot. In response to this need, a client-server version of MSTPA, MSTPA Lite, has been streamlined for application of embedded processors on the robots, and additional data products for the comparison of MSTPA Lite with observations have been added to the on-board real-time signal processing. With these modifications it is now possible for the robots to update the MSTPA Lite model in-mission to provide better agreement between predictions and observations, therefor informing onboard autonomy algorithms with better information on which to base helm decisions. Results are shown for data collected near La Spezia Italy in October 2017.

The underwater environment of the sea bottom is complex, and it is easy to be affected by light, underwater impurities and shooting angle. Because of the dense and mutual occlusion of underwater targets, the collected images are not clear, fuzzy and easy to be resolved, which affects the accuracy of target detection and recognition. Aiming at the above problems, this paper proposes an improved YOLOV5 method for underwater seafood target detection. Firstly, the C3 module of high-level features is fused with swin transformer to create the C3STR module, and the improved C3STR module can enlarge the receptive field of the network, obtain the global information better and increase the ability of feature extraction, the DC3 module is constructed by adding convolution to the low-level feature C3 module, which improves the model detection ability with a little more computation. Finally, the network feature fusion module is improved, which integrates the deep-level information with the shallow-level information, the combination of semantic information and position information can improve the precision of model recognition and enhance the ability of target detection. The experimental results show that the detection accuracy of the improved YOLOv5 algorithm is increased to 88.3%, which is 2% higher than that of the original YOLOv5 algorithm.

We consider underwater target detection by using a novel active, self-contained and rapidly deployable underwater inflatable co-prime sonar array (UICSA). In particular, we measure the received signal strength (RSS) and angle-of-arrival (AoA) of acoustic signals reflected by an underwater target. Measurements from different positions of the transmitter with respect to the UICSA are organized in a three mode real-valued tensor. Then, the conformity of each entry with respect to all other data points in the tensor is calculated based on recursively refined calculations of $L_{1}$ -norm tensor subspaces. Conformity values are then used for the detection of an underwater target. We evaluate the data conformity of RSS and AoA recordings acquired from the testbed deployment of a seven-element UICSA prototype and three underwater acoustic transmitters at Florida Atlantic University. We show for the first time that conformity evaluation over multi-modal data measurements can accurately detect the presence of an underwater target.

The underwater environment is more complex than that on land, resulting in severe static and dynamic blurring in underwater images, reducing the recognition accuracy of underwater targets and failing to meet the needs of underwater environment detection. Firstly, for the static blurring problem, we propose an adaptive color compensation algorithm and an improved MSR algorithm. Secondly, for the problem of dynamic blur, we adopt the Restormer network to eliminate the dynamic blur caused by the combined effects of camera shake, camera out-of-focus and relative motion displacement, etc. then, through qualitative analysis, quantitative analysis and underwater target detection on the enhanced dataset, the feasibility of our underwater enhancement method is verified. Finally, we propose a target recognition network suitable for the complex underwater environment. The local and global information is fused through the CCBC module and the ECLOU loss function to improve the positioning accuracy. The FasterNet module is introduced to reduce redundant computations and parameter counting. The experimental results show that the CFEC-YOLOv7 model and the underwater image enhancement method proposed by us exhibit excellent performance, can better adapt to the underwater target recognition task, and have a good application prospect.

Underwater robots are an important tool for exploiting marine resources, while underwater target detection is a key technology for marine fishing by underwater robots. For the problem that the traditional algorithm is difficult to detect small targets and multiple scales in the underwater environment, this paper proposes an underwater biological detection algorithm based on the multi-scale feature fusion and attention mechanism. First, a YOLOv5 network is constructed, and a bi-directionally weighted BiFPN feature pyramid structure is fed into the neck network so that multiscale target features can be efficiently merged. Second, a channel and spatial convolutional attention mechanism is introduced between the neck network and the prediction network in order to increase the saliency of the underwater target that needs to be detected, which effectively reduces the missed and erroneous detection of underwater targets. The experimental results show that the proposed algorithm can accurately detect multi-scale underwater targets in complex underwater environments with an average accuracy of 80.18%, which is 2.87% better than YOLOv5, and an average recall of 85.06%, which is 4.81% better than YOLOv5.

Active sonar systems are used in the detection and localization of underwater targets. While traditional approaches use pulsed active sonar (PAS) to transmit short bursts, high duty cycle (HDC) sonar systems have been the focus of recent research and can overcome the shortcomings of PAS. Since HDC sonar systems transmit a long pulse train waveform, we must address sub-pulse interference issues, which requires multiple orthogonal sub-pulses and generalized sinusoidal frequency modulated (GSFM) pulses are suitable for this purpose. Unfortunately, conventional GSFM pulse train design methods do not generate an adequate number of orthogonal sub-pulses. Therefore, we propose an improved GSFM pulse train waveform design approach for overcoming the limitations of these conventional methods. The proposed method is organized into two parts, the first focused on the assessment of the auto-correlation, and the second focused on the optimizing the orthogonality between sub-pulses. Cost function is also carefully designed for this purpose. From simulation experiments, we found that the proposed method was able to produce 30 orthogonal sub-pulses and an optimized waveform that demonstrated better detection performance than conventional waveforms under most conditions. We also verified the performance of the proposed method via actual sea experiments, with analysis showing superior performance matching that of simulations. An analysis on the bandwidth parameter K is also conducted and it is found K = 1.25 to be the best option.

The tracking of underwater targets represents a basic unit in underwater surveillance for offering effective search and rescue operations. However, the tracking of the target is a major constraint in finding the underwater target. This paper devises a model for underwater target tracking considering radar signals. Radar signals are subjected to the image reconstruction process to make them suitable for further processing. The gridding is the next step, which is utilized for generating the grids to focus on each region in a precise manner. The features like Ridgelet transform and Local Gabor XOR Pattern (LGXP) are produced. Data augmentation is the next process, which helps to reduce the size of data by performing resizing. At last, the tracking of targets is performed from each grid with a Deep neuro fuzzy network (DNFN). Here, DNFN training is performed with Exponential-Competitive Swarm Optimization (E-CSO), which is derived by integrating Exponential Weighted Moving Average (EWMA) and Competitive Swarm Optimization (CSO). The proposed E-CSO-based DNFN offered high efficiency with a maximal detection rate of 98.8%, minimal Mean square error of 0.012, and Mean Absolute Percentage Error (MAPE) of 17.883.