Multi-Modal Multi-Stage Underwater Side-Scan Sonar Target Recognition Based on Synthetic Images

Wang, Jian; Li, Haisen; Huo, Guanying; Li, Chao; Wei, Yuhang

doi:10.3390/rs15051303

Cited by 7 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recognition accuracy of this method was much higher than the traditional manual feature extraction and support vector machine classification. Target recognition from sonar images also relies on the accuracy of direction information [118]. Based on the CNN algorithm, Zhang proposed a new orientation estimation technology based on wavelet image energy ratio.…”

Section: Other Technical Applicationsmentioning

confidence: 99%

Sonar image intelligent processing in seabed pipeline detection: review and application

Shi,

Cao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Subsea pipelines rely primarily on imaging sonar for detection and identification. We analyze the imaging principles of side scan sonar, multi-beam sonar, synthetic aperture sonar, seafloor penetrating sonar and forward-looking sonar. We discuss their effectiveness in detecting seabed pipelines, as well as their limitations in image recognition capabilities. As intelligent algorithms have become increasingly important in the field of image processing, we review the sonar image intelligent detection and recognition algorithms in the past six years and summarize the internal principles and application effects of classic algorithms such as SIFT (Scale-Invariant Feature Transform), KMA (K-means algorithm), and CFAR (Constant False-Alarm Rate) that currently show good application prospects. Simultaneously, we review the particular strengths exhibited by these algorithms, such as contour feature extraction, image segmentation and clustering, target recognition under background noise, etc. The research on intelligent processing of sonar images opens up a new way to solve the difficult problem of the seabed targets detection and recognition.

show abstract

Section: Other Technical Applicationsmentioning

confidence: 99%

Sonar image intelligent processing in seabed pipeline detection: review and application

Shi,

Cao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Scholars have researched sonar synthetic image datasets [2,3] and zero-shot learning methods [4,11,14,20] to augment samples to overcome the shortage of samples and simulate sonar images. Pre-trained DCNNs and fine-tuning techniques are powerful methods for sonar image detection [21,22].…”

Section: Related Workmentioning

confidence: 99%

“…The advancement of sonar technology has yielded remarkable achievements in underwater exploration [1] and target detection [2,3]. Compared with the limitations of optical sensors in detecting targets, such as short detection distances and poor underwater visibility, SSS-based target detection methods have become increasingly popular and effective.…”

Section: Introductionmentioning

confidence: 99%

Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning

Xi,

2024

JMSE

View full text Add to dashboard Cite

There are many challenges in using side-scan sonar (SSS) images to detect objects. The challenge of object detection and recognition in sonar data is greater than in optical images due to the sparsity of detectable targets. The complexity of real-world underwater scanning presents additional difficulties, as different angles produce sonar images of varying characteristics. This heterogeneity makes it difficult for algorithms to accurately identify and detect sonar objects. To solve these problems, this paper presents a novel method for sonar image target detection based on a transformer and YOLOv7. Thus, two data augmentation techniques are introduced to improve the performance of the detection system. The first technique applies stain-like noise to the training optical image data to simulate the real sonar image environment. The second technique adds multiple shadows to the optical image and 3D data targets to represent the direction of the target in the sonar image. The proposed method is evaluated on a public sonar image dataset, and the experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed. The experimental results show that our method achieves better precision.

show abstract

“…Acoustic sensing technology is a highly effective technique in the field of remote sensing, utilizing the physical properties of sound [1][2][3][4][5][6][7][8][9][10][11]. In the last decade, considerable progress has been made in improving the signal-to-noise ratio (SNR) in electroacoustic sensor device applications.…”

Section: Introductionmentioning

confidence: 99%

A Nonlinear Gradient-Coiling Metamaterial for Enhanced Acoustic Signal Sensing

Hao,

Zhao,

Han

2023

Crystals

View full text Add to dashboard Cite

Acoustic sensing systems play a critical role in identifying and determining weak sound sources in various fields. In many fault warning and environmental monitoring processes, sound-based sensing techniques are highly valued for their information-rich and non-contact advantages. However, noise signals from the environment reduce the signal-to-noise ratio (SNR) of conventional acoustic sensing systems. Therefore, we proposed novel nonlinear gradient-coiling metamaterials (NGCMs) to sense weak effective signals from complex environments using the strong wave compression effect coupled with the equivalent medium mechanism. Theoretical derivations and finite element simulations of NGCMs were executed to verify the properties of the designed metamaterials. Compared with nonlinear gradient acoustic metamaterials (Nonlinear-GAMs) without coiling structures, NGCMs exhibit far superior performance in terms of acoustic enhancement, and the structures capture lower frequencies and possess a wider angle acoustic response. Additionally, experiments were constructed and conducted using set Gaussian pulse and harmonic acoustic signals as emission sources to simulate real application scenarios. It is unanimously shown that NGCMs have unique advantages and broad application prospects in the application of weak acoustic signal sensing, enhancement and localization.

show abstract

Multi-Modal Multi-Stage Underwater Side-Scan Sonar Target Recognition Based on Synthetic Images

Cited by 7 publications

References 36 publications

Sonar image intelligent processing in seabed pipeline detection: review and application

Sonar image intelligent processing in seabed pipeline detection: review and application

Sonar Image Target Detection Based on Simulated Stain-like Noise and Shadow Enhancement in Optical Images under Zero-Shot Learning

A Nonlinear Gradient-Coiling Metamaterial for Enhanced Acoustic Signal Sensing

Contact Info

Product

Resources

About