Sonar Image

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 5799 Experts worldwide ranked by ideXlab platform

Son-cheol Yu - One of the best experts on this subject based on the ideXlab platform.

  • Realistic Sonar Image Simulation Using Generative Adversarial Network
    IFAC-PapersOnLine, 2020
    Co-Authors: Minsung Sung, Son-cheol Yu
    Abstract:

    Abstract Sonar sensors are widely utilized underwater because they can observe long-ranged objects and are tolerant to measurement conditions, such as turbidity and light conditions. However, Sonar Images have low quality and hard to collect, so development and application of Sonar-based algorithms are difficult. This paper proposes a method to generate realistic Sonar Images or to segment real Sonar Image, to better utilize the Sonar sensors. A simple Sonar Image simulator was implemented using a ray-tracing method. The simulator could calculate semantic information of real Sonar Images including properties of highlight, background, and shadow regions. Then, a generative adversarial network translated the simulated Images into more realistic Images or real Sonar Images into simulated-like Images. The proposed method can be used to augment or pre-process Sonar Images.

  • Convolutional-Neural-Network-based Underwater Object Detection Using Sonar Image Simulator with Randomized Degradation
    OCEANS 2019 MTS IEEE SEATTLE, 2019
    Co-Authors: Minsung Sung, Seokyong Song, Young-woon Song, Son-cheol Yu
    Abstract:

    This paper proposes a method to detect underwater objects using Sonar Image simulator and convolutional neural network (CNN). Instead of simulating very realistic Sonar Images which is computationally complex, we implemented a simple Sonar simulator that calculates only semantic information. Then, we generated training Images of target objects by adding randomized degradation effects to the simulated Images. The CNN trained with these generated Images is robust to the degradation effects inherent in Sonar Images and thus can detect target objects in real Sonar Images. We verified the proposed method using the Sonar Images captured at sea through field experiments. The proposed method can implement object detection more easily because it only uses simulated Images instead of real Sonar Images which are challenging to acquire. The proposed method can also be applied to other Sonar-Image-based algorithms.

  • Sonar Image Translation Using Generative Adversarial Network for Underwater Object Recognition
    2019 IEEE Underwater Technology (UT), 2019
    Co-Authors: Minsung Sung, Son-cheol Yu
    Abstract:

    Sonar sensor is widely used for underwater object recognition. However, acquiring reference Sonar Images for each target object is high-cost and time-consuming. Sonar Image simulators can generate reference Sonar Images with small computation, but the simulated Images are different with actual Sonar Images captured in the field. This paper proposes a method to translate actual Sonar Images to simulated-like Images using a generative adversarial network. We trained the network with Images captured by the indoor water tank test. The trained neural network can generate simulator-like Images from given actual Sonar Images. Further, we can recognize the target object using template matching between the translated Image and the reference Images simulating the target object.

  • Crosstalk Removal in Forward Scan Sonar Image Using Deep Learning for Object Detection
    IEEE Sensors Journal, 2019
    Co-Authors: Minsung Sung, Son-cheol Yu
    Abstract:

    This paper proposes the detection and removal of crosstalk noise using a convolutional neural network in the Images of forward scan Sonar. Because crosstalk noise occurs near an underwater object and distorts the shape of the object, underwater object detection is limited. The proposed method can detect crosstalk noise using the neural network and remove crosstalk noise based on the detection result. Thus, the proposed method can be applied to other Sonar-Image-based algorithms and enhance the reliability of those algorithms. We applied the proposed method to a three-dimensional point cloud generation and generated a more accurate point cloud. We verified the performance of the proposed method by performing multiple indoor and field experiments.

  • Denoising auto-encoder based Image enhancement for high resolution Sonar Image
    2017 IEEE Underwater Technology (UT), 2017
    Co-Authors: Seokyong Song, Son-cheol Yu
    Abstract:

    A typical Sonar Image has a plenty of random noise compared to an optical Image. Due to poor picture quality, there is a large restriction on recognizing any object. Pattern recognition is exceedingly difficult not only in computer Image processing but even in human eyes. Numerous researchers have attempted to apply various types of average filters to Sonar Images, and have also removed noise by using multiple Images in succession. However, each of the algorithms has a limitation in that the resolution of the Image itself is degraded or the Image of the object is difficult to remove noise. Finally, We performed Sonar Image noise reduction with the auto-encoder algorithm based on convolutional neural network, which as recently been attracting attention. With the algorithm, we obtained Sonar Images of superior quality with only a single continuous Image. We simply learned a ton of Sonar Images in a neural network of auto-encoder structures, and then we could get the results by injecting the original Sonar Images. We verified the results of Image enhancement using the acoustic lens based multibeam Sonar Images.

Xiufen Ye - One of the best experts on this subject based on the ideXlab platform.

  • Geometric Correction Method of Side-scan Sonar Image
    OCEANS 2019 - Marseille, 2019
    Co-Authors: Xiufen Ye, Haibo Yang
    Abstract:

    In recent decades, side-scan Sonar technology has been used for underwater surveying, and its applications include marine mapping, shipwreck salvage, target detection, geological exploration and etc. Side-scan Sonar is usually equipped on AUV. According to the imaging principle of side-scan Sonar, besides the dynamic change of AUV heading, the speed and attitude instability will also cause geometric distortion of the side-scan Sonar Image. Therefore, it is necessary to correct the side-scan Sonar Image before further processing it. In this paper, we study on the side-scan Sonar Image geometric correction method including slant range correction and speed correction. Analyzing the limitations of the slant range correction method mentioned in the existing literature, we proposes an improved method by establishing a correction model. Secondly, We use GPS information from Sonar data to correct the influence of side-scan Sonar Image caused by the change of AUV speed. At last, the effectiveness of the proposed method is verified by experiments.

  • Research on Side-scan Sonar Image Target Classification Method Based on Transfer Learning
    OCEANS 2018 MTS IEEE Charleston, 2018
    Co-Authors: Xiufen Ye, Chuanlong Li, Siyuan Zhang, Peng Yang, Xiang Li
    Abstract:

    In this paper, we propose a method which combine transfer learning method and deep learning method for side-scan Sonar Image classification task. The application of deep learning method can effectively improve the accuracy of classification and use transfer learning method to overcome the problem that the deep neural networks cannot be applied due to the small number of training samples. We fine-tune a pre-trained convolutional neural network (CNN) primarily trained for common Image classification tasks where sufficient training data exists, make it specifically optimized for a side-scan Sonar Image classification task, we also present the pre-processing method for the source domain training samples which can influence the transfer efficiency. Experiments show that this method can effectively prevent the overfitting problem of training the deep neural network under small sample number conditions, and at the same time guarantees the high classification accuracy.

  • Fully affine invariant matching algorithm based on nonlinear scale space for side scan Sonar Image
    2015 IEEE International Conference on Mechatronics and Automation (ICMA), 2015
    Co-Authors: Xiufen Ye, Peng Li, Jianguo Zhang
    Abstract:

    A fully affine invariant matching method for side scan Sonar Image is proposed in this paper. This method uses fully affine invariant features under nonlinear scale space built by nonlinear diffusion filter. We call the new Nonlinear Affine Inva-Riant feature NAIR feature, it makes full use of the advantage of affine invariant of ASIFT algorithm and feature distinctiveness in nonlinear scale space. It overcomes the problem of the failure of large view-changed side scan Sonar Image matching caused by the change of heading direction during Sonar data acquisition and the anti-noise performance is enhanced through the nonlinear diffusion filter. The experimental results show that the proposed method has better anti-noise performance and higher accuracy compared with the state of art feature matching algorithms.

  • An improved spectral clustering Sonar Image segmentation method
    The 2011 IEEE ICME International Conference on Complex Medical Engineering, 2011
    Co-Authors: Hongyu Bian, Xiufen Ye
    Abstract:

    Image segmentation method based on the existing spectrum clustering algorithm cannot accurately segment Sonar Image because of the ambiguous object edge, extremely complex noisy background and critical shadow impact of Sonar Image, and aiming at this problem, this paper proposed an improved spectrum clustering Sonar Image segmentation method. First of all, to overcome negative impact of the Sonar Image shadow and achieve selective segmentation of Sonar target, morphological top-hat transformation and bottom-hat transformation were used for Sonar Image preprocessing; Secondly, Image segmentation based on spectrum clustering was done after preprocessing and an improved spectral clustering Sonar Image segmentation system was constructed; Finally, simulation experiment was taken and the results showed that the proposed method is more suitable for Sonar Image segmentation.

  • Sonar Image segmentation on Fuzzy C-Mean using local texture feature
    The 2011 IEEE ICME International Conference on Complex Medical Engineering, 2011
    Co-Authors: Xiufen Ye, Lei Wang, Tian Wang
    Abstract:

    This paper proposes an improved Fuzzy C-Mean (FMC) algorithm for scan Sonar Image segmentation. Taking care of the characteristics of Sonar Images which are poor contrast, low resolution and strong noise, we propose to use local texture features and original Image to calculate the distance of the pixels and the center of clusters .First, we use the Gauss-Markov Random Field (GMRF) model to extract Local texture features. Then, we form a new FMC clustering criterion to complete the Sonar Image segmentation. Experimental data show that the segmentation results of our clustering method are superior to the standard FMC and.

Enfang Sang - One of the best experts on this subject based on the ideXlab platform.

  • Sonar Image denoising based on HMT model in morphological wavelet domain
    2010 International Conference on Image Analysis and Signal Processing, 2010
    Co-Authors: Enfang Sang, Hongyu Bian, Zhengyan Shen, Yuanshou Li
    Abstract:

    Sonar Images are susceptible to noise pollution that results in low contrast. And Sonar Image denoising technology is the key for subsequent target recognition. In this paper, an Image denoising algorithm using wavelet transform was studied. Firstly, we constructed a morphological mean wavelet for gray Image processing. Then the noisy Sonar Image was trained by the Hidden Markov Tree model in the morphological wavelet domain. According to the characteristics of the morphological mean wavelet, we classified multiresolution analysis of the noisy Image in different directions, and removed noise according to the training result with Bayesian estimation. Finally, a desired denoising effect could be obtained by computing the average of different reconstructed Images. Computer experiments show that our denoising algorithm can remove Gaussian noise of Sonar Image effectively. Compared with some classical wavelet denoising methods, Image details are retained better.

  • Sonar Image segmentation based on implicit active contours
    2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, 2009
    Co-Authors: Enfang Sang, Zhengyan Shen, Yuanshou Li
    Abstract:

    Sonar Images are susceptible to noise pollution and the Image intensities are often inhomogeneous. So there are many difficulties in Sonar Image segmentation. When apply the current popular region-based active contour models to Sonar Image segmentation, the objects we interested may be segmented inaccurately sometimes, especially for the Image with shadows. To solve the problem, a simple algorithm was proposed in this paper. Firstly we analyzed the initial contour action in level set evolution, and then combined with a strict local binary fitting energy we segmented Sonar Images selectively by changing the initial contour. Computer experiment results show that our method is very suitable for Sonar Image segmentation. Target regions with weak border can be obtained perfectly. And for the Sonar Image with shadows, interested objects and the shadows could be distinguished separately, avoiding the boundary leaking problems caused by the shadows' existing.

  • Sonar Image Classification Based on Directional Wavelet and Fuzzy Fractal Dimension
    2007 2nd IEEE Conference on Industrial Electronics and Applications, 2007
    Co-Authors: Yingli Wang, Enfang Sang
    Abstract:

    This paper presents a supervised classification method of Sonar Image, which takes advantages of both directional wavelet (DW) and fuzzy fractal dimension (FFD). The definition of FFD is an extension of the pixel-covering method by incorporating the fuzzy set. DW is used for the decomposition of original Images. In the process of feature extraction, a feature set is obtained by estimating the FFD of the directional wavelet transform sub-Images. In the part of classifier construction, the learning vector quantization (LVQ) network is adopted as a classifier. Experiments of Sonar Image classification have been carried out with satisfactory results, which verify the effectiveness of this method.

Huuthu Nguyen - One of the best experts on this subject based on the ideXlab platform.

  • study on the classification performance of underwater Sonar Image classification based on convolutional neural networks for detecting a submerged human body
    Sensors, 2019
    Co-Authors: Huuthu Nguyen
    Abstract:

    Auto-detecting a submerged human body underwater is very challenging with the absolute necessity to a diver or a submersible. For the vision sensor, the water turbidity and limited light condition make it difficult to take clear Images. For this reason, Sonar sensors are mainly utilized in water. However, even though a Sonar sensor can give a plausible underwater Image within this limitation, the Sonar Image’s quality varies greatly depending on the background of the target. The readability of the Sonar Image is very different according to the target distance from the underwater floor or the incidence angle of the Sonar sensor to the floor. The target background must be very considerable because it causes scattered and polarization noise in the Sonar Image. To successfully classify the Sonar Image with these noises, we adopted a Convolutional Neural Network (CNN) such as AlexNet and GoogleNet. In preparing the training data for this model, the data augmentation on scattering and polarization were implemented to improve the classification accuracy from the original Sonar Image. It could be practical to classify Sonar Images undersea even by training Sonar Images only from the simple testbed experiments. Experimental validation was performed using three different datasets of underwater Sonar Images from a submerged body of a dummy, resulting in a final average classification accuracy of 91.6% using GoogleNet.

Yan Zhou - One of the best experts on this subject based on the ideXlab platform.

  • A Robust and Fast Method for Sidescan Sonar Image Segmentation Using Nonlocal Despeckling and Active Contour Model
    IEEE Transactions on Cybernetics, 2017
    Co-Authors: Simon X. Yang, Qingwu Li, Yan Zhou
    Abstract:

    Sidescan Sonar Image segmentation is a very important issue in underwater object detection and recognition. In this paper, a robust and fast method for sidescan Sonar Image segmentation is proposed, which deals with both speckle noise and intensity inhomogeneity that may cause considerable difficulties in Image segmentation. The proposed method integrates the nonlocal means-based speckle filtering (NLMSF), coarse segmentation using k-means clustering, and fine segmentation using an improved region-scalable fitting (RSF) model. The NLMSF is used before the segmentation to effectively remove speckle noise while preserving meaningful details such as edges and fine features, which can make the segmentation easier and more accurate. After despeckling, a coarse segmentation is obtained by using k-means clustering, which can reduce the number of iterations. In the fine segmentation, to better deal with possible intensity inhomogeneity, an edge-driven constraint is combined with the RSF model, which can not only accelerate the convergence speed but also avoid trapping into local minima. The proposed method has been successfully applied to both noisy and inhomogeneous Sonar Images. Experimental and comparative results on real and synthetic Sonar Images demonstrate that the proposed method is robust against noise and intensity inhomogeneity, and is also fast and accurate.