Present status and challenges of underwater acoustic target recognition technology: A review

Lei, Zhufeng; Xiaofang, Lei; Wang, Na; Zhang, Qingyang

doi:10.3389/fphy.2022.1044890

Cited by 13 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The energy efficiency of lightweight models suits it for power-limited devices like autonomous underwater vehicles. Lei et al [31] highlighted the necessity to avoid computational expenses in future underwater acoustic information processing. Some algorithmic methods, including depth-separable convolution [32], extrusion and excitation [26], asymmetric convolution [33], and architecture search [34,35], have emerged as useful tools for building lightweight networks.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Network Based on Multi-Scale Asymmetric Convolutional Neural Networks with Attention Mechanism for Ship-Radiated Noise Classification

Yan,

Yao

et al. 2024

JMSE

View full text Add to dashboard Cite

Ship-radiated noise classification is critical in ocean acoustics. Recently, the feature extraction method combined with time–frequency spectrograms and convolutional neural networks (CNNs) has effectively described the differences between various underwater targets. However, many existing CNNs are challenging to apply to embedded devices because of their high computational costs. This paper introduces a lightweight network based on multi-scale asymmetric CNNs with an attention mechanism (MA-CNN-A) for ship-radiated noise classification. Specifically, according to the multi-resolution analysis relying on the relationship between multi-scale convolution kernels and feature maps, MA-CNN-A can autonomously extract more fine-grained multi-scale features from the time–frequency domain. Meanwhile, the MA-CNN-A maintains its light weight by employing asymmetric convolutions to balance accuracy and efficiency. The number of parameters introduced by the attention mechanism only accounts for 0.02‰ of the model parameters. Experiments on the DeepShip dataset demonstrate that the MA-CNN-A outperforms some state-of-the-art networks with a recognition accuracy of 98.2% and significantly decreases the parameters. Compared with the CNN based on three-scale square convolutions, our method has a 68.1% reduction in parameters with improved recognition accuracy. The results of ablation explorations prove that the improvements benefit from asymmetric convolution, multi-scale block, and attention mechanism. Additionally, MA-CNN-A shows a robust performance against various interferences.

show abstract

Section: Introductionmentioning

confidence: 99%

A Lightweight Network Based on Multi-Scale Asymmetric Convolutional Neural Networks with Attention Mechanism for Ship-Radiated Noise Classification

Yan,

Yao

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Due to the complexity of the marine environment, numerous techniques have been proposed to obtain better tracking performance, such as acoustic, electromagnetic, etc [3]. However, the innovation in technology and the evolving "stealth" technology of underwater targets pose significant challenges to target detection systems [4]. Therefore, traditional target tracking methods are difficult to use for tracking underwater targets stably and accurately [5].…”

Section: Introductionmentioning

confidence: 99%

An Underwater Target Wake Detection in Multi-Source Images Based on Improved YOLOv5

Shi

2023

IEEE Access

View full text Add to dashboard Cite

In the marine environment, underwater targets improve "stealth" performance through innovation in technology, so traditional target tracking methods are difficult to use for tracking underwater targets stably and accurately. This paper proposes an improved YOLOv5 (You Look Only Once) based method to detect wake of underwater target accurately in multi-source images. We obtain optical images and thermal images through model simulation and scaled experiment. Improve the generalization ability of the detection network through data augmentation. The proposed method introduces linear features detection to enhance feature propagation, and promote feature reuse. The result shows that the proposed method is better than the original object detection algorithms. The improved algorithm can detect underwater targets status (underwater or surface) and image types (optical wake or thermal wake).

show abstract

“…This notion of redundancy in ResNet was echoed by Xue et al, who observed a drop in identification rates by adding more residual layers [23]. Looking ahead, Lei et al highlight a pivotal research direction: minimizing computational expenses in underwater acoustic data processing [24]. Current methodologies often grapple with striking a harmonious balance between accuracy and efficiency in deep learning applications.…”

Section: Introductionmentioning

confidence: 99%

Model for Underwater Acoustic Target Recognition with Attention Mechanism Based on Residual Concatenate

Chen,

Xie,

Chen

et al. 2023

JMSE

View full text Add to dashboard Cite

Underwater acoustic target recognition remains a formidable challenge in underwater acoustic signal processing. Current target recognition approaches within underwater acoustic frameworks predominantly rely on acoustic image target recognition models. However, this method grapples with two primary setbacks; the pronounced frequency similarity within acoustic images often leads to the loss of critical target data during the feature extraction phase, and the inherent data imbalance within the underwater acoustic target dataset predisposes models to overfitting. In response to these challenges, this research introduces an underwater acoustic target recognition model named Attention Mechanism Residual Concatenate Network (ARescat). This model integrates residual concatenate networks combined with Squeeze-Excitation (SE) attention mechanisms. The entire process culminates with joint supervision employing Focal Loss for precise feature classification. In our study, we conducted recognition experiments using the ShipsEar database and compared the performance of the ARescat model with the classic ResNet18 model under identical feature extraction conditions. The findings reveal that the ARescat model, with a similar quantity of model parameters as ResNet18, achieves a 2.8% higher recognition accuracy, reaching an impressive 95.8%. This enhancement is particularly notable when comparing various models and feature extraction methods, underscoring the ARescat model’s superior proficiency in underwater acoustic target recognition.

show abstract

Present status and challenges of underwater acoustic target recognition technology: A review

Cited by 13 publications

References 41 publications

A Lightweight Network Based on Multi-Scale Asymmetric Convolutional Neural Networks with Attention Mechanism for Ship-Radiated Noise Classification

A Lightweight Network Based on Multi-Scale Asymmetric Convolutional Neural Networks with Attention Mechanism for Ship-Radiated Noise Classification

An Underwater Target Wake Detection in Multi-Source Images Based on Improved YOLOv5

Model for Underwater Acoustic Target Recognition with Attention Mechanism Based on Residual Concatenate

Contact Info

Product

Resources

About