Synthetic Sonar Image Simulation with Various Seabed Conditions for Automatic Target Recognition

Shin, Jane; Chang, Shi; Bays, Matthew J.; Weaver, Joshua N.; Wettergren, Thomas A.; Ferrari, Silvia

doi:10.1109/oceans47191.2022.9977275

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, research into automatic detection methods for underwater targets is of great significance. Some scholars have adopted machine learning techniques, combined with manual features and classification technologies, to achieve automated underwater target detection [6,7]. However, these methods are limited when dealing with complex seabed environments, as Side-scan sonar images often suffer from low resolution, insufficient features, high noise, and deformation.…”

Section: Introductionmentioning

confidence: 99%

Sample Augmentation Method for Side-Scan Sonar Underwater Target Images Based on CBL-sinGAN

Peng,

Jin,

Bian

et al. 2024

JMSE

View full text Add to dashboard Cite

The scarcity and difficulty in acquiring Side-scan sonar target images limit the application of deep learning algorithms in Side-scan sonar target detection. At present, there are few amplification methods for Side-scan sonar images, and the amplification image quality is not ideal, which is not suitable for the characteristics of Side-scan sonar images. Addressing the current shortage of sample augmentation methods for Side-scan sonar, this paper proposes a method for augmenting single underwater target images using the CBL-sinGAN network. Firstly, considering the low resolution and monochromatic nature of Side-scan sonar images while balancing training efficiency and image diversity, a sinGAN network is introduced and designed as an eight-layer pyramid structure. Secondly, the Convolutional Block Attention Module (CBAM) is integrated into the network generator to enhance target learning in images while reducing information diffusion. Finally, an L1 loss function is introduced in the network discriminator to ensure training stability and improve the realism of generated images. Experimental results show that the accuracy of shipwreck target detection increased by 4.9% after training with the Side-scan sonar sample dataset augmented by the proposed network. This method effectively retains the style of the images while achieving diversity augmentation of small-sample underwater target images, providing a new approach to improving the construction of underwater target detection models.

show abstract

Section: Introductionmentioning

confidence: 99%

Sample Augmentation Method for Side-Scan Sonar Underwater Target Images Based on CBL-sinGAN

Peng,

Jin,

Bian

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…14 Sonar simulators are developed to generate synthetic sonar images, offering another solution to the data scarcity challenge and unknown environmental conditions. 15 Joe et al 16 have employed simulators for two different sonar sensors to create sonar fusion-based mapping algorithms. Kim et al 17 have simulated sonar images representing different object shapes to validate their algorithms for three-dimensional reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Cycle-GAN-based synthetic sonar image generation for improved underwater classification

Koo,

Youm,

Shin

2024

Ocean Sensing and Monitoring XVI

View full text Add to dashboard Cite

Synthetic Sonar Image Simulation with Various Seabed Conditions for Automatic Target Recognition

Cited by 2 publications

References 23 publications

Sample Augmentation Method for Side-Scan Sonar Underwater Target Images Based on CBL-sinGAN

Sample Augmentation Method for Side-Scan Sonar Underwater Target Images Based on CBL-sinGAN

Cycle-GAN-based synthetic sonar image generation for improved underwater classification

Contact Info

Product

Resources

About