Sonar Image Segmentation Research Articles

Side-Scan Sonar Image Segmentation Based on Multi-Channel Fusion Convolution Neural Networks

Side-scan sonar is an important application in the field of ocean exploration. Accurate segmentation of target regions in side-scan sonar images is a challenging issue due to the low-resolution and strong noise interference. To accurately and faster segment the different categories target in sonar image, a novel convolutional neural networks (CNNs) model is proposed in this study. Firstly, the deep separable residual module is used for target regions multi-scale feature extraction and suppression noise feature information interference, and the multi-channel feature fusion method is used to enhance feature information transfer of convolution layers. Secondly, the adaptive supervised function is used for pixel-wise classification of different categories targets. Finally, to improve model generalization ability and robustness, the adaptive transfer learning method is introduced in the model training process. We have performed extensive experiments on side-scan sonar image with different targets and scales. The experimental results show that the detection accuracy of the proposed method reaches 95.73%, which is outperforms other state-of-the-art methods on the side-scan sonar image segmentation tasks. Moreover, the method has fewer computational parameters, facilitating future deployment it to underwater mobile detection devices.

Underwater sonar image segmentation combining pixel-level and region-level information

Side-scan sonar (SSS) has been increasingly utilized in underwater exploration, due to the low energy attenuation of the acoustic wave in water. However, SSS imaging is characterized by its high speckle noises, strong intensity bias and low spatial resolution, which pose challenges to accurately delineate objects in underwater sonar images. This issue is handled by our proposed model that segments sonar images via combining pixel-level and region-level information. Pixel-to-pixel and region-to-region neighboring relations are considered in this model. Formally, the unified Markov random field (UMRF) is combined with the level set (LS) to establish a novel energy function for segmenting underwater sonar images. In such a model, the pixel-level information and region-level information are synergistically integrated by UMRF to force LS evolution. Results obtained by our model convergence can accurately segment underwater sonar images into three partitions: the object, shadow and background. From experimental analysis, our proposed model achieves an excellent tradeoff between the segmentation accuracy and noise resistance in underwater sonar image segmentation. The average correctness of our model reaches 0.9431 which has more than 7% improved to the best conventional method.

Fused Adaptive Receptive Field Mechanism and Dynamic Multiscale Dilated Convolution for Side-Scan Sonar Image Segmentation

Side-scan sonar (SSS) is a vital sensor for marine survey, which is widely used in military and civilian fields. The accurate segmentation of SSS images is critical in sonar image intelligent interpretation. Existing SSS image segmentation methods have several limitations, such as insufficient feature extraction, relatively worse segmentation results for tiny target categories, and serious interference by seabed reverberation noise and bright shadow region. To overcome these issues, we propose a novel encoder-decoder architecture SSS image segmentation method based on convolution neural network (CNN). First, we extract the multi-scale feature information contained in target region using the dynamic multi-scale dilated convolution (DMDC_Conv). Second, to further obtain the global and detail feature information, we construct the adaptive receptive field mechanism block (ARFM_Block). Third, we design a feature fusion attention mechanism block (FFAM_Block) to fuse high-level and low-level feature information with different scales and suppress background information interference. Final, we construct a tree structure optimization module (TSOM) to solve the problem of pixel misclassification and obtain refine SSS image segmentation results. Extensive experiments are carried out on the constructed real scene SSS image dataset. The experimental results show that the proposed method achieves 93.24% and 90.82% of MPA and MIoU, respectively, which outperforms other state-of-the-art methods and has a substantial advantage in inference speed and calculation parameters.

Underwater Sonar Image Segmentation by a Novel Joint Level Set Model

This paper proposes a novel joint level set model for underwater sonar image segmentation. Combining features in points and regions in our novel joint level set (LS), it can achieve excellent performance for underwater sonar image segmentation. Regional information guides the model to locate the object of interest, whereas the point information accurately delineates contours. In addition, the unified Markov random field (UMRF) is taken to measure the neighboring relation between points and regions, which can overcome the problems of the high speckle noise, strong bias and low resolution of underwater sonar images. Our novel model can segment underwater sonar images into three partitions, such as the objects of interest, shadow and backgrounds. In contrast to current segmentation methods, outstanding results are demonstrated by our model. Moreover, another advantage of our model lies in its high efficiency.

Iterative, Deep Synthetic Aperture Sonar Image Segmentation

Synthetic aperture sonar (SAS) systems produce high-resolution images of the seabed environment. Moreover, deep learning has demonstrated superior ability in finding robust features for automating imagery analysis. However, the success of deep learning is conditioned on having lots of labeled training data, but obtaining generous pixel-level annotations of SAS imagery is often practically infeasible. This challenge has thus far limited the adoption of deep learning methods for SAS segmentation. Algorithms exist to segment SAS imagery in an unsupervised manner, but they lack the benefit of state-of-the-art learning methods and the results present significant room for improvement. In view of the above, we propose a new iterative algorithm for unsupervised SAS image segmentation combining superpixel formation, deep learning, and traditional clustering methods. We call our method Iterative Deep Unsupervised Segmentation (IDUS). IDUS is an unsupervised learning framework that can be divided into four main steps: 1) A deep network estimates class assignments. 2) Low-level image features from the deep network are clustered into superpixels. 3) Superpixels are clustered into class assignments (which we call pseudo-labels) using $k$-means. 4) Resulting pseudo-labels are used for loss backpropagation of the deep network prediction. These four steps are performed iteratively until convergence. A comparison of IDUS to current state-of-the-art methods on a realistic benchmark dataset for SAS image segmentation demonstrates the benefits of our proposal even as the IDUS incurs a much lower computational burden during inference (actual labeling of a test image). Finally, we also develop a semi-supervised (SS) extension of IDUS called IDSS and demonstrate experimentally that it can further enhance performance while outperforming supervised alternatives that exploit the same labeled training imagery.

A Robust and Fast Method for Sidescan Sonar Image Segmentation Based on Region Growing.

For high-resolution side scan sonar images, accurate and fast segmentation of sonar images is crucial for underwater target detection and recognition. However, due to the characteristics of low signal-to-noise ratio (SNR) and complex environmental noise of sonar, the existing methods with high accuracy and good robustness are mostly iterative methods with high complexity and poor real-time performance. For this purpose, a region growing based segmentation using the likelihood ratio testing method (RGLT) is proposed. This method obtains the seed points in the highlight and the shadow regions by likelihood ratio testing based on the statistical probability distribution and then grows them according to the similarity criterion. The growth avoids the processing of the seabed reverberation regions, which account for the largest proportion of sonar images, thus greatly reducing segmentation time and improving segmentation accuracy. In addition, a pre-processing filtering method called standard deviation filtering (STDF) is proposed to improve the SNR and remove the speckle noise. Experiments were conducted on three sonar databases, which showed that RGLT has significantly improved quantitative metrics such as accuracy, speed, and segmentation visual effects. The average accuracy and running times of the proposed segmentation method for 100 × 400 images are separately 95.90% and 0.44 s.

A Local Region-Based Level Set Method With Markov Random Field for Side-Scan Sonar Image Multi-Level Segmentation

Side-scan sonar is widely utilized in the field of underwater exploration. Accurate segmentation of the side-scan sonar images is an essential part of sonar image processing. To improve the accuracy of image segmentation and reduce the occupancy of computing resources, a new active contour model for image segmentation is proposed in this article. Firstly, we make the energy function of each pixel determined by itself and its neighbors. This article embeds the local texture neighborhood region system and define its structure to against the noise and object boundary pollution of the image. Further, we introduce a Bayesian framework that embeds the Markov Random Field model and local texture information to counteract the problem of intensity inhomogeneity, improve the accuracy of segmentation, and reduce computational cost. Finally, according to this model, we customize a new multi-class energy function which applied to the level set function. By minimizing this energy equation, we can divide the image into three classes: object, shadow, and seabed background. The experimental results show that this method has a good effect on the synthesized high-noise sonar images and real sonar images, and also have significantly increased the accurate recognition of underwater targets.

A review on the wavelet methods for sonar image segmentation

The sonar image segmentation is needed such as in underwater object orientation and recognition, in collision prevention and navigation of underwater robots, in underwater investigation and rescue, in seafloor object seeking, in seafloor salvage, and in marine military affairs like torpedo detection. The wavelet-based methods have the ability of multiscale and multiresolution, and they are apt at edge detection and feature extraction of images. The applications of these methods to the sonar image segmentation are increasingly raised. The contents of the article are to classify the sonar image segmentation methods with wavelets and to describe main ideas, advantages, disadvantages, and conditions of use of every method. In the methods for sonar image region (or texture) segmentation, the thought of multiscale (or multiresolution) analysis of the wavelet transform is usually combined with other theories or methods such as the clustering algorithms, the Markov random field, co-occurrence matrix, Bayesian theory, and support vector machine. In the methods for sonar image edge detection, the space–frequency local characteristics of the wavelet transform are usually utilized. The wavelet packet-based and beyond wavelet-based methods can usually reach more precise segmentation. The article also gives 12 directions (or development trends predicted) of the sonar image segmentation methods with wavelets which should be researched deeply in the future. The aim of writing this review is to make the researchers engaged in sonar image segmentation learn about the research works in the field in a short time. Up to now, the similar reviews in this field have not been found.

Robust A*-Search Image Segmentation Algorithm for Mine-like Objects Segmentation in SONAR Images

This paper addresses a sonar image segmentation method employing a Robust A*-Search Image Segmentation (RASIS) algorithm. RASIS is applied on Mine-Like Objects (MLO) in sonar images, where an object is defined by highlight and shadow regions, i.e. regions of high and low pixel intensities in a side-scan sonar image. RASIS uses a modified A*-Search method, which is usually used in mobile robotics for finding the shortest path where the environment map is predefined, and the start/goal locations are known. RASIS algorithm represents the image segmentation problem as a path-finding problem. Main modification concerning the original A*-Search is in the cost function that takes pixel intensities and contour curvature in order to navigate the 2D segmentation contour. The proposed method is implemented in Matlab and tested on real MLO images. MLO image dataset consist of 70 MLO images with manta mine present, and 70 MLO images with cylinder mine present. Segmentation success rate is obtained by comparing the ground truth data given by the human technician who is detecting MLOs. Measured overall success rate (highlight and shadow regions) is 91% for manta mines and 81% for cylinder mines.

Fuzzy Preprocessing and Clustering Analysis Method of Underwater Multiple Targets in Forward Looking Sonar Image for AUV Tracking

Marine sonar image noise absorption under water can result in poor image quality, low image resolution and blurred target contour. This paper proposes a systematic framework including underwater image fuzzy preprocessing method, and clustering based on the principal component analysis (PCA) of underwater targets. Underwater images were denoised adopting fast median filtering algorithm with mean acceleration. The fuzzing mathematics were not only developed with the aim of improving the visual quality of underwater sonar images, but also involved in the sonar image segmentation for extracting the target area from the suspicious area. Both the geometric and statistical features were treated as features in PCA algorithm. As demonstrated by the experimental results, visual quality of the sonar image was improved, multi-target threshold segmentation was achieved and multiple targets could be analyzed and clustered for stably tracking AUV.

Unsupervised Local Spatial Mixture Segmentation of Underwater Objects in Sonar Images

In this paper, we focus on the segmentation of sonar images to achieve underwater object detection and classification. Our goal is to achieve accurate segmentation of the object's highlight and shadow regions. We target a robust solution that can manage different seabed backgrounds. Segmentation of sonar images is a challenging task. Speckle noise and intensity inhomogeneity may cause false detections and complex seabed textures, such as sand ripples and seagrass, often leading to false segmentation. In this paper, we propose our local spatial mixture (LSM) method for image segmentation of sidescan deployed sonar systems of any type. This new method estimates pixel labels in sonar images by incorporating the possible spatial correlation between neighboring pixels for improved segmentation. LSM modifies the expectation–maximization algorithm by adding an intermediate step (I-step) between the expectation (E-step) and maximization (M-step) steps. To combat intensity inhomogeneity, we employ a new initialization algorithm, one whose thresholds are set automatically to achieve and maintain robustness in various underwater environments. Using multiple evaluation indexes that measure the geometrical features of the segmented objects, we tested LSM using synthetic and real sonar images, one of which is obtained from our own sea experiment. Our results show that LSM achieves improved segmentation performance over the state-of-the-art methods of four different approaches; LSM is also robust to different seabed textures and intensity inhomogeneity. We share the sonar images from our sea experiments.

Segmentation of sonar images with intensity inhomogeneity based on improved MRF

Sonar is one of the most important tools for underwater object detection and submarine topography reconstruction. To classify sonar images automatically and accurately is essential for the navigation and path planning of autonomous underwater vehicles (AUV). However, for the intensity inhomogeneity and speckle noise in sonar images, it is difficult to obtain segmentation results of high accurate rate. To address these issues, in this paper, we advocate a segmentation method incorporating simple linear iterative clustering (SLIC) and adaptive intensity constraint into Markov random field (MRF), to segment sonar images with intensity inhomogeneity into the object highlight, the object shadow and the background areas. The main procedures of the proposed work are as follows: first, SLIC is used to separate sonar images into homogeneous super pixels, and second the homogeneity patches, with a novel intensity constraint strategy, is utilized to optimize the segmentation result of MRF at each iteration. Experimental results reveal that the proposed method performs well and fast on real sonar images which have intensity inhomogeneity problem.

Enhanced Fuzzy-based Local Information Algorithm for Sonar Image Segmentation.

The recent boost in undersea operations has led to the development of high-resolution sonar systems mounted on autonomous vehicles. These vehicles are used to scan the seafloor in search of different objects such as sunken ships, archaeological sites, and submerged mines. An important part of the detection operation is the segmentation of sonar images, where the object's highlight and shadow are distinguished from the seabed background. In this work, we focus on the automatic segmentation of sonar images. We present our enhanced fuzzybased with Kernel metric (EnFK) algorithm for the segmentation of sonar images which, in an attempt to improve segmentation accuracy, introduces two new fuzzy terms of local spatial and statistical information. Our algorithm includes a preliminary de-noising algorithm which, together with the original image, feeds into the segmentation procedure to avoid trapping to local minima and to improve convergence. The result is a segmentation procedure that specifically suits the intensity inhomogeneity and the complex seabed texture of sonar images. We tested our approach using simulated images, real sonar images, and sonar images that we created in two different sea experiments, using multibeam sonar and synthetic aperture sonar. The results show accurate segmentation performance that is far beyond the stateof-the-art results.

Segmentation of Sonar Image on Seafloor Sediments Based on Multiclass SVM

ABSTRACT Chen, J. and Zhang, S., 2018. Segmentation of sonar image on seafloor sediments based on multiclass SVM. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 597–602. Coconut Creek (Florida), ISSN 0749-0208. Because the seabed sediment sonar image has the complex background and low noise-signal ratio, the existing image segmentation methods are difficult to extract different types of sonar image features from the complex background of seabed sediment sonar image. The image segmentation accuracy is low. Thus, this paper presents a method for segmenting seabed sediment sonar image based on multiclass SVM. Firstly, the seabed sediment sonar image was denoised to extract the statistical feature, texture feature and gray feature with phase consistency. Then they were composed into characteristic sample vectors of multidimensional seabed sediment sonar image. Finally, SVM classification method was used to segment the...

Segmentation of Sidescan Sonar Imagery Using Markov Random Fields and Extreme Learning Machine

As a widely used segmentation scheme, Markov random field (MRF) utilizes $k$ -means clustering to calculate the initial model for sidescan sonar image segmentation. However, for the noise and intensity inhomogeneity nature of the sidescan sonar images, the segmentation results of $k$ -means clustering have low accuracy, motivating us to use machine learning methods to initialize MRF. Meanwhile, an extreme learning machine (ELM), a supervised learning algorithm derived from the single-hidden-layer feedforward neural networks, learns faster than randomly generated hidden-layer parameters and is superior to a support vector machine (SVM). Therefore, in this paper, we proposed a novel method for sidescan sonar image segmentation based on MRF and ELM. The proposed method segments sidescan sonar images in object-highlight, object-shadow, and sea-bottom reverberation areas. Specifically, we intend to use an ELM to get an initial model for MRF. Moreover, to improve the stability of an ELM, a simple ensemble ELM (SE-ELM) based on an ensemble algorithm is utilized to obtain the prediction model. In an SE-ELM, we use an ensemble of ELMs and majority votes to determine the prediction of testing data sets. Then, the classification results of the SE-ELM are utilized to initialize MRF, termed as SE-ELM-MRF. With features consisting of pixels of small image patches, our experiments on real sonar data indicate that the SE-ELM performs better than other machine learning methods such as ELM, kernel-based extreme learning machine, SVM, and convolutional neural networks. Moreover, using SE-ELM as the initial method in the proposed SE-ELM-MRF, the segmentation results are smoother and the segmentation process converges faster than the traditional MRF.

Sonar image segmentation and quality assessment using prominent image processing techniques

Sound navigation and ranging (SONAR) is a technique that uses sound propagation to navigate, communicate or to detect objects on or under the surface of the water. It even forecasts what lies beneath the sea waves. It uses sound waves to observe the happenings occurring on the region of seafloor. Sonar images that are framed using sound waves are not directly suitable for analysis as it would be affected primarily by a speckle noise which misguides the way of interpretation. The metaphors of substances in those images are very important in the field of oceanography to suit many applications. The scope of this research work is to promote the quality of an image in order to get a better interpretation than using a raw image. This article also deals with the novel work to identifying the type of noise present in sonar image using an artificial neural network (ANN) and the overall accuracy of the network achieved is found to be 93.37%. In addition, filtration of noise has been done using different digital filters and it is proved that the combination of SRAD and Gaussian filter is best suited for sonar image denoising processes. Finally, this work contributes many ideas related to the segmentation of objects in an image using various techniques like Fuzzy C Means (FCM), K means, Expectation–maximization (EM) algorithm, Otsu thresholding and Toboggan Segmentation. The research outcomes are compared with different quality matrices and it exhibits that the FCM segmentation has high accuracy than the other methods and all the results were validated through MATLAB software.

A sonar image segmentation algorithm based on quantum-inspired particle swarm optimization and fuzzy clustering

The underwater sonar image has the characteristics of complex background and heavy noise pollution. By using multi-bit quantum system to encode particles, a new sonar image segmentation algorithm based on quantum-inspired particle swarm and fuzzy clustering is proposed. Based on its own optimal particles and global optimal particles, the rotation angle is determined. By calculating the variance of the particle group fitness, the multi-bit quantum revolving gate is used to update the particle position in real time. The output of improved particle swarm optimization is used to initialize the K-mean clustering center to converge to the global optimal solution. Based on the idea of fuzzy membership matrix in FCM, combined with the isolated spatial information characteristics of the noise, the sonar image segmentation and the denoising are carried out. The experimental results show that the proposed algorithm can improve the global search ability of particle swarm optimization effectively. It is better than the quantum fuzzy clustering and quantum genetic algorithm in image segmentation. The analysis results of multiple real underwater sonar images show that the new optimization algorithm has faster convergence speed, better optimizing capacity and better segmentation results for sonar images.

Side scan sonar image segmentation and synthesis based on extreme learning machine

This paper presents side scan sonar (SSS) image segmentation and synthesis methods based on extreme learning machine (ELM). As an algorithm derived from single-hidden layer feedforward neural networks (SLFNs), ELM has superior performance and fast learning speed with randomly generated hidden layer parameters. The SSS image segmentation uses ELM as a classifier with features generated by convolutional neural network (CNN) of multiple pathways. The CNN of multiple pathways can learn local and global features from SSS images adaptively. Taking these features as input, ELM assigns the central pixel of each input image patch of CNN to one class. Moreover, the presented SSS image synthesis method utilizes ELM as a regression algorithm, in which the non-parametric sampling algorithm is used first to synthesize coarse SSS images according to segmentation maps and sample images for each class. Then ELM trained with the coarse synthesis images and their ground truth maps (the Gaussian-filtered SSS images) synthesizes fine SSS images. Furthermore, peak signal to noise ratio (PSNR) of the synthetic SSS images with the Gaussian-filtered SSS images as ref is used as one evaluation metric for segmentation performance. Experimental results demonstrate that the SSS image segmentation method combining convolutional features with ELM outperforms typical CNN and support vector machine (SVM), and the presented SSS image synthesis method and the evaluation metric are applicable.

Image side-scan sonar segmentation for seafloor detection in Lembeh strait, Bitung, North Sulawesi

Segmentation is the process of dividing and grouping the pixel of an image into a segments or objects with the similar characteristics into homogenous areas. This method is expected to get better result with relatively faster result compared to manual (digitation) method. Side-scan Sonar image segmentation using Multi-resolution segmentation algorithm with considered many parameter and using pixel based threshold. The segment grouping using spectral reference by emphasizing the degree of brightness and texture where the two parameters are related to each. Segmentation with two parameters (brightness and texture) is effectively used for targets located near a towfish because of higher target spectral heterogeneity. TVG (Time Varried Gain) correction deliver more detailed result, image with TVG have highest accuracy of 0.987. This proves that the TVG correction that regulates the backscatter to affect the hue in the image has an important role in the seafloor classification process, in addition it can sharpen the appearance of the target which is far from the tow-fish range. Weakness of energy during measurement caused by angle and distance from instrument to target far from the towfish will affect the value of brightness and texture.

Research on Convolutional Neural Network Model for Sonar IMAGE Segmentation

The speckle noise of sonar images affects the human interpretation and automatic recognition of images seriously. It is important and difficult to realize the precision segmentation of sonar image with speckle noise in the field of image processing. Full convolution neural network (FCN) has the advantage of accepting arbitrary size image and preserving spatial information of original input image. In this paper, the image features are obtained by autonomic learning of convolutional neural network, the original learning rules based on the mean square error loss function is improved. Taking the pixel as the processing unit, the segmentation method based on FCN model with relative loss function(FCN-RLF) for small submarine sonar image is proposed, sonar image pixel-level segmentation is achievied. Experimental results show that the improved algorithm can improve the segmentation accuracy and keep the edge and detail of sonar image better. The proposed model has better ability to reject sonar image speckle noise.