Side scan sonar image augmentation for sediment classification using deep learning based transfer learning approach

Chandrashekar, Gurrala; Raaza, Arun; Rajendran, V.; Ravikumar, D.

doi:10.1016/j.matpr.2021.07.222

Cited by 9 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transducers are arranged on both sides of the towed body with different working frequencies to send acoustic pulse signals to both sides of the seabed. When the signal encounters different objects in the water, the acoustic pulse signal will reflect visual information with different intensities [39,40].…”

Section: Side Scan Sonarmentioning

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: Side Scan Sonarmentioning

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

“…This finding underscores the potential significance of TL in transferring recognition of SSS targets. Chandrashekar et al [33] employed the sample TL (STL) strategy, originally developed for optical images, to accurately classify underwater sediments in SSS images. Yu et al [34,35] harnessed TL to devise a target detection method, incorporating two loss functions, namely, position and target recognition errors in the head network.…”

Section: Related Workmentioning

confidence: 99%

An Underwater Side-Scan Sonar Transfer Recognition Method Based on Crossed Point-to-Point Second-Order Self-Attention Mechanism

Wang,

Li,

Dong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Recognizing targets through side-scan sonar (SSS) data by deep learning-based techniques has been particularly challenging. The primary challenge stems from the difficulty and time consumption associated with underwater acoustic data acquisition, which demands systematic explorations to obtain sufficient training samples for accurate deep learning-based models. Moreover, if the sample size of the available data is small, the design of effective target recognition models becomes complex. These challenges have posed significant obstacles to developing accurate SSS-based target recognition methods via deep learning models. However, utilizing multi-modal datasets to enhance the recognition performance of sonar images through knowledge transfer in deep networks appears promising. Owing to the unique statistical properties of various modal images, transitioning between different modalities can significantly increase the complexity of network training. This issue remains unresolved, directly impacting the target transfer recognition performance. To enhance the precision of categorizing underwater sonar images when faced with a limited number of mode types and data samples, this study introduces a crossed point-to-point second-order self-attention (PPCSSA) method based on double-mode sample transfer recognition. In the PPCSSA method, first-order importance features are derived by extracting key horizontal and longitudinal point-to-point features. Based on these features, the self-supervised attention strategy effectively removes redundant features, securing the second-order significant features of SSS images. This strategy introduces a potent low-mode-type small-sample learning method for transfer learning. Classification experiment results indicate that the proposed method excels in extracting key features with minimal training complexity. Moreover, experimental outcomes underscore that the proposed technique enhances recognition stability and accuracy, achieving a remarkable overall accuracy rate of 99.28%. Finally, the proposed method maintains high recognition accuracy even in noisy environments.

show abstract

“…To study the applicability of different CNN models in target recognition in SSS images, the CNN-based networks DCNN [12], ECNet [13], YOLOv3 [14], VGG-19, and ResNet50 [15] were all used for recognition and obtained good prediction accuracies. To reduce the impact of a small amount of data on prediction accuracy, Sung et al [16] proposed a GAN-based method for generating realistic SSS images to address the problem of the insufficient data volume of SSS images of the seafloor, which can generate images of SSS image types to help train the model.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

Sun

Song

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the development of deep learning techniques, convolutional neural networks (CNN) are increasingly being used in image recognition for marine surveys and underwater object classification. Automatic recognition of targets on side-scan sonar (SSS) images using CNN can improve recognition accuracy and efficiency. However, the vast selection of CNN models makes it challenging to select models for target recognition in SSS images. Therefore, this paper aims to compare different CNN models’ prediction accuracy and computational performance comprehensively. First, four traditional CNN models were applied to train and predict the same submarine SSS dataset using both the original model and models with transfer learning methods. Then, we examined and studied the prediction accuracy and computation performance of four CNN models. Results showed that transfer learning enhances the accuracy of all CNN models, with lesser improvements for AlexNet and VGG-16 and greater improvements for GoogleNet and ResNet101. GoogleNet has the highest prediction of accuracy (100% in the train dataset and 94.27% in the test dataset) and good computational difficulty. The findings of this work are useful for future model selection in target recognition in SSS images.

show abstract

Side scan sonar image augmentation for sediment classification using deep learning based transfer learning approach

Cited by 9 publications

References 21 publications

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

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

An Underwater Side-Scan Sonar Transfer Recognition Method Based on Crossed Point-to-Point Second-Order Self-Attention Mechanism

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

Contact Info

Product

Resources

About