An efficient method for the simulation of multireceiver SAS raw signal

IntroductionExisting methods primarily focus on earth acoustic parameters inversion under specific layered structures. However, they face challenges with experimental data from unknown seabed stratification, hindering accurate parameter inversion.MethodsTo address this, a novel algorithm combines Back Propagation Neural Network (BPNN) for distinguishing seabed stratification and inverting acoustic parameters. Simulated sound pressure data disturb seabed parameters as input, enabling feature recognition for training the neural network inversion model. Acoustic parameters are then estimated under identified stratification using the sound field model.ResultsThe inversion model is validated using simulation and pool shrinkage data. Results show the neural network model effectively stratifies simulation and experimental data, providing accurate inversion results for acoustic parameters corresponding to distinct layers.DiscussionThe neural network model's accuracy and practicality are confirmed through hierarchical judgment of scale test data and acoustic parameter inversion. This approach introduces a new perspective for shallow sea acoustic parameter inversion, offering a promising application scenario.

Section: Simulation Results Analysismentioning

confidence: 99%

A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

Wang,

Cui,

Zhu

et al. 2024

“…The image enhancement method proposed in this paper is able to achieve pleasing results, but whether it is beneficial to the high-level domain deserves further investigation. In addition, current underwater imagery consists mainly of sonar imaging (Zhang et al, 2021b;Zhang, 2023) and optical camera imaging. Since sonar imaging uses acoustic signals while camera imaging uses optical signals, there are significant differences between the two methods.…”

Section: Discussionmentioning

confidence: 99%

A learnable full-frequency transformer dual generative adversarial network for underwater image enhancement

Zheng,

Wang,

Zheng

et al. 2024

Underwater applications present unique challenges such as color deviation, noise, and low contrast, which can degrade image quality. Addressing these issues, we propose a novel approach called the learnable full-frequency transformer dual generative adversarial network (LFT-DGAN). Our method comprises several key innovations. Firstly, we introduce a reversible convolution-based image decomposition technique. This method effectively separates underwater image information into low-, medium-, and high-frequency domains, enabling more thorough feature extraction. Secondly, we employ image channels and spatial similarity to construct a learnable full-frequency domain transformer. This transformer facilitates interaction between different branches of information, enhancing the overall image processing capabilities. Finally, we develop a robust dual-domain discriminator capable of learning spatial and frequency domain characteristics of underwater images. Extensive experimentation demonstrates the superiority of the LFT-DGAN method over state-of-the-art techniques across multiple underwater datasets. Our approach achieves significantly improved quality and evaluation metrics, showcasing its effectiveness in addressing the challenges posed by underwater imaging. The code can be found at https://github.com/zhengshijian1993/LFT-DGAN.

“…In fact, the proposed SUS-YOLOv5 can directly detect the sea cucumber and the other some marine organisms in this paper. Whereas, our proposed algorithm cannot be directly applied to all image processing and object detection scenarios, such as synthetic aperture sonar (SAS) (Yang, 2023;Zhang, 2023) and radar (SAR) (Pinheiro et al, 2015). We believe that our algorithm can be indirectly applied to these fields or the further improved algorithms on the basis of our algorithm can be extended to apply to these fields.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Multi-object detection and behavior tracking of sea cucumbers with skin ulceration syndrome based on deep learning

Ge,

Xuan,

Lou

et al. 2024

Skin ulceration syndrome of sea cucumbers is one of the most serious diseases in intensive aquaculture, and it is the most effective way of preventing the spread of this disease to detect the abnormal behavior of sea cucumbers in time and take corresponding measures. However, the detection and tracking of multi-object is a hard problem in sea cucumber behavior analysis. To solve this problem, this paper first proposes a novel one-stage algorithm SUS-YOLOv5 for multi-object detection and tracking of sea cucumbers. The proposed SUS-YOLOv5 optimizes the maximum suppression algorithm in the overlapping region of the object detection box. Next, the SE-BiFPN feature fusion structure is proposed to enhance the transmission efficiency of feature information between deep and shallow layers of the network. Then, a MO-Tracking algorithm is proposed integrated with DeepSORT to achieve real-time multi-object tracking. Experimental results show that the mAP@0.5 and mAP@0.5:0.95 of the proposed object detector reach 95.40% and 83.80%, respectively, which are 3.30% and 4.10% higher than the original YOLOv5s. Compared with the traditional SSD, YOLOv3, and YOLOv4, the mAP of SUS-YOLOv5 is improved by 5.49%, 1.57%, and 3.76%, respectively. This research can realize the multi-object detection and tracking, which lays the foundation for the prediction of skin ulceration syndrome in sea cucumbers and has a certain practical application value for improving the intelligence level of aquaculture.