Classification Of Sidescan Sonar Images Research Articles

SI-GAT: Enhancing Side-Scan Sonar Image Classification Based on Graph Structure

SI-GAT: Enhancing Side-Scan Sonar Image Classification Based on Graph Structure

Shuffle-RDSNet: a method for side-scan sonar image classification with residual dual-path shrinkage network

Shuffle-RDSNet: a method for side-scan sonar image classification with residual dual-path shrinkage network

Side-Scan Sonar Image Classification With Zero-Shot and Style Transfer

Side-Scan Sonar Image Classification With Zero-Shot and Style Transfer

Lambertian-based adversarial attacks on deep-learning-based underwater side-scan sonar image classification

Deep convolutional neural networks (CNNs) are extensively applied to the classification tasks for Side-scan sonar (SSS) images. However, state-of-the-art neural networks are prone to be confused by adversarial attacks that generate a tiny modification of the images, threatening the security of SSS classification. The robustness of CNN to adversarial attacks can be improved by introducing adversarial examples through adversarial training. Practical adversarial examples are often generated from elaborate adversarial attackers. For the underwater scenario of sonar, a specially designed adversarial attack method to weaken SSS image classification can make the research community better understand the weakness of CNN in this scenario and improve the security measures in a well-directed way. Thus, exploring adversarial attack methods for SSS image classification is essential. Nevertheless, the existing adversarial attack methods are designed for optical images, reflecting no physical characteristics of sonar images. To fill this gap and investigate the adversarial attack related to real-world conditions, in this paper, we propose an adversarial attack method named Lambertian Adversarial Sonar Attack (LASA). It initially leverages the Lambertian model to simulate the formation of the SSS image, factoring the image to three parameters, then updates the parameters on the direction of gradients by the chain rule. Finally, the parameters regenerate the adversarial example to fool the classifier. To validate the performance of LASA, we constructed a diversified SSS image dataset containing three categories. On our dataset, LASA reduces the Top-1 accuracy of a well-trained ResNet-101 to 7.31%±0.21 (one-shot version) and 0.00% (iterative version), the success rate of targeted attack reaches 97.03±2.24, far beyond the performance of the existing state-of-the-art adversarial attack methods. Meanwhile, we show that the adversarial training using examples generated from LASA makes the classifier more robust. We expect that our methods can be applied as a benchmark of adversarial attacks on SSS images, motivating future research to design novel neural networks or defensive methods to resist real-world adversarial attacks on SSS images.

A Texture Feature Removal Network for Sonar Image Classification and Detection

Deep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most effective way to address such scenarios. However, there is a large domain gap between optical images and sonar images, and common transfer learning methods may not be able to effectively handle it. In this paper, we propose a transfer learning method for sonar image classification and object detection called the texture feature removal network. We regard the texture features of an image as domain-specific features, and we narrow the domain gap by discarding the domain-specific features, and hence, make it easier to complete knowledge transfer. Our method can be easily embedded into other transfer learning methods, which makes it easier to apply to different application scenarios. Experimental results show that our method is effective in side-scan sonar image classification tasks and forward-looking sonar image detection tasks. For side-scan sonar image classification tasks, the classification accuracy of our method is enhanced by 4.5% in a supervised learning experiment, and for forward-looking sonar detection tasks, the average precision (AP) is also significantly improved.

Dual-Path Residual "Shrinkage" Network for Side-Scan Sonar Image Classification.

The underwater environment is complicated and changeable and contains many noises, making it difficult to detect a particular object in the underwater environment. At present, the main seabed detection technology explores the seabed environment with sonar equipment. However, the characteristics of underwater sonar imaging (e.g., low contrast, blurred edges, poor texture, and unsatisfactory quality) have serious negative influences on such image classification. Therefore, in this study, we propose a dual-path deep residual “shrinkage” network (DP-DRSN) module, which is a simple and effective neural network attention module that can classify side-scan sonar images. Specifically, the module can extract background and feature texture information of the input feature mapping through different scales (e.g., global average pooling and global max pooling), whereas scale information passes through a two-layer 1 × 1 convolution to increase nonlinearity. This helps realize cross-channel information interaction and information integration simultaneously before outputting threshold parameters in a sigmoid layer. The parameters are then multiplied by the average value of the input feature mapping to obtain a threshold, which is used to denoise the image features using the soft threshold function. The proposed DP-DRSN study provided higher classification accuracy and efficiency than other models. In this way, the feasibility and effectiveness of DP-DRSN in image classification of side-scan sonar are proven.

A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification

Due to the strong speckle noise caused by the seabed reverberation which makes it difficult to extract discriminating and noiseless features of a target, recognition and classification of underwater targets using side-scan sonar (SSS) images is a big challenge. Moreover, unlike classification of optical images which can use a large dataset to train the classifier, classification of SSS images usually has to exploit a very small dataset for training, which may cause classifier overfitting. Compared with traditional feature extraction methods using descriptors—such as Haar, SIFT, and LBP—deep learning-based methods are more powerful in capturing discriminating features. After training on a large optical dataset, e.g., ImageNet, direct fine-tuning method brings improvement to the sonar image classification using a small-size SSS image dataset. However, due to the different statistical characteristics between optical images and sonar images, transfer learning methods—e.g., fine-tuning—lack cross-domain adaptability, and therefore cannot achieve very satisfactory results. In this paper, a multi-domain collaborative transfer learning (MDCTL) method with multi-scale repeated attention mechanism (MSRAM) is proposed for improving the accuracy of underwater sonar image classification. In the MDCTL method, low-level characteristic similarity between SSS images and synthetic aperture radar (SAR) images, and high-level representation similarity between SSS images and optical images are used together to enhance the feature extraction ability of the deep learning model. Using different characteristics of multi-domain data to efficiently capture useful features for the sonar image classification, MDCTL offers a new way for transfer learning. MSRAM is used to effectively combine multi-scale features to make the proposed model pay more attention to the shape details of the target excluding the noise. Experimental results of classification show that, in using multi-domain data sets, the proposed method is more stable with an overall accuracy of 99.21%, bringing an improvement of 4.54% compared with the fine-tuned VGG19. Results given by diverse visualization methods also demonstrate that the method is more powerful in feature representation by using the MDCTL and MSRAM.

Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks

Side-scan sonar is widely used in underwater rescue and the detection of undersea targets, such as shipwrecks, aircraft crashes, etc. Automatic object classification plays an important role in the rescue process to reduce the workload of staff and subjective errors caused by visual fatigue. However, the application of automatic object classification in side-scan sonar images is still lacking, which is due to a lack of datasets and the small number of image samples containing specific target objects. Secondly, the real data of side-scan sonar images are unbalanced. Therefore, a side-scan sonar image classification method based on synthetic data and transfer learning is proposed in this paper. In this method, optical images are used as inputs and the style transfer network is employed to simulate the side-scan sonar image to generate “simulated side-scan sonar images”; meanwhile, a convolutional neural network pre-trained on ImageNet is introduced for classification. In this paper, we experimentally demonstrate that the maximum accuracy of target classification is up to 97.32% by fine-tuning the pre-trained convolutional neural network using a training set incorporating “simulated side-scan sonar images”. The results show that the classification accuracy can be effectively improved by combining a pre-trained convolutional neural network and “similar side-scan sonar images”.

SUPPORT VECTOR MACHINE AND DECISION TREE BASED CLASSIFICATION OF SIDE-SCAN SONAR MOSAICS USING TEXTURAL FEATURES

Abstract. The diversity and heterogeneity of coastal, estuarine and stream habitats has led to them becoming a prevalent topic for study. Woody ruins are areas of potential riverbed habitat, particularly for fish. Therefore, the mapping of those areas is of interest. However, due to the limited visibility in some river systems, satellites, airborne or other camera-based systems (passive systems) cannot be used. By contrast, sidescan sonar is a popular underwater acoustic imaging system that is capable of providing high- resolution monochromatic images of the seafloor and riverbeds. Although the study of sidescan sonar imaging using supervised classification has become a prominent research subject, the use of composite texture features in machine learning classification is still limited. This study describes an investigation of the use of texture analysis and feature extraction on side-scan sonar imagery in two supervised machine learning classifications: Support Vector Machine (SVM) and Decision Tree (DT). A combination of first- order texture and second-order texture is investigated to obtain the most appropriate texture features for the image classification. SVM, using linear and Gaussian kernels along with Decision Tree classifiers, was examined using selected texture features. The results of overall accuracy and kappa coefficient revealed that SVM using a linear kernel leads to a more promising result, with 77% overall accuracy and 0.62 kappa, than SVM using either a Gaussian kernel or Decision Tree (60% and 73% overall accuracy, and 0.39 and 0.59 kappa, respectively). However, this study has demonstrated that SVM using linear and Gaussian kernels as well as a Decision Tree makes it capable of being used in side-scan sonar image classification and riverbed habitat mapping.

Multiaspect Classification of Sidescan Sonar Images: Four Different Approaches to Fusing Single-Aspect Information

In this paper, the classification of an object on the seabed from two sidescan sonar looks is considered. Four different approaches to fusing the information from the individual looks are described. The first method uses a kernel regression classification method with the combined feature (CF) vectors from the two looks. The other three approaches are based upon the Dempster-Shafer (DS) fusion of the outputs from a single-look kernel-based classifier. They differ with respect to the manner in which the DS masses for each look are derived from the single-look classifier. The four approaches are evaluated with Klein 5500 sidescan sonar data collected from four classes: rock and three dummy mine types: manta, rockan, and cylinder. The sonar data were collected in October 2005 when the Defence Research and Development Canada Atlantic (DRDC-Atlantic, Dartmouth, NS, Canada), participated with the NATO Undersea Research Centre (NURC, La Spezia, Italy) and Groupe D'Etudes Sous-Marines de l'Atlantique (GESMA, Brest, France) in a joint trial (CITADEL) with the DRDC remote, semisubmersible vehicle DORADO. Using these data, it is shown that two of the approaches for DS mass assignments yield two-look classification performances very similar to each other and to the CF method. The DS approaches have the advantage that they do not require explicit training with a CF set.

Two Dimensional Wavelet Coefficient Statistics for Sea Bottom Classification

In this paper we examine the classification of different seafloors based on the analysis of images obtained by side-scan sonar. For this purpose, we apply various two dimensional multilevel wavelet decomposition schemes on images obtained from three different seafloor types, i.e., sand ripples, rocks and sands, and then we examine the statistics of the corresponding wavelet coefficients. The observed Probability Density Functions (pdf) are modeled using various theoretical distributions such as the Alpha Stable, Sum of Gaussians, Log-normal. The parameters of the fit are subsequently used to classify the side scan sonar images according to well known cluster analysis techniques. The use of the energy of the wavelet coefficients as a tool for side scan sonar image classification is also evaluated. A new unsupervised classification scheme based on the pdf fitting parameters is proposed.

Feature-based texture classification of side-scan sonar images using a neural network approach

A texture classification system for side-scan sonar images by using a trained multilayer feedforward neural network (MFNN) is presented. The system classified textures by exploiting principal feature patterns, giving a high correct-classification rate. Experimental examples for the classification of side-scan sonar images are provided.

Remote sensing of the sea-bed using fractal techniques

With the increase in the demand for high-quality sidescan sonar imagery of the sea-bed, there is a need for the development of fast and accurate computer techniques for the analysis of the survey information. The paper describes some techniques that have been developed to perform operator-assisted and fully automated classification of sidescan sonar images of the sea-bed on the basis of sediment texture. Special reference is made to the usefulness of the fractal model for the analysis and synthesis of textures.