The Experts below are selected from a list of 309 Experts worldwide ranked by ideXlab platform

Bo He - One of the best experts on this subject based on the ideXlab platform.

  • Segmentation of Side Scan Sonar Images on AUV
    2019 IEEE Underwater Technology (UT), 2019
    Co-Authors: Fei Yu, Guangliang Li, Qi Wang, Kaige Li, Meihan Wu, Bo He
    Abstract:

    Side Scan Sonar is an active Sonar. It uses seafloor backscattering to obtain the topographic information of the seabed, and constructs seabed topographic image information, which is the basis of seabed imaging. For AUV equipped with Side Scan Sonar, the interpretation of Sonar images is beneficial to enhance their autonomy. Based on efficient and accurate segmentation algorithm, the efficiency and accuracy of target recognition can be ensured. Therefore, how to automatically extract and understand marine information in acoustic images becomes the current research hotspot. Related work such as classification of marine targets, detection of underwater targets, etc. Real-time image acquired by the Side Scan Sonar carried by AUV. In order to better identify the seabed information, we combine data augmentation, super-resolution technology, deep learning, and Markov random field(MRF). First, perform data preprocessing, getting marine data sets is very difficult and expensive. For small data sets are not sufficient to support deep network, and in order to prevent overfitting, we have performed data augmentation. Second, because the data collected by the Sonar contains more noise, in order to achieve better image recognition, we introduced a super-resolution technology to process the low-resolution image into a high resolution image. Third, we perform image segmentation for the processed data. During this process, the resolution of the data collected by the Side Scan Sonar is very low. In order to avoid the images as the network deepens, receptive field is getting smaller and smaller, so that more noise is added, we have adopted the DeepLab network framework. Finally, in order to better reflect the generalization ability of the network, so that the network has better performance, we take into account the label information of the nearby image, the Markov random field(MRF) was introduced at the back end. Experiments show that this method has better results.

  • Classification and mosaicking of Side Scan Sonar image
    OCEANS 2017 - Aberdeen, 2017
    Co-Authors: Yan Song, Guangliang Li, Chen Feng, Bo He
    Abstract:

    As an underwater detection sensor, Side-Scan Sonar plays an important role in marine survey, mineral exploration, underwater archaeology and so on. During the use of Side-Scan Sonar, classifiication and mosaicking of collected images is essential in most cases. There are two main contributions in our work. On the one hand, we propose a supervised learning method based on kernel-based extreme learning machine (KELM) to perform image classification. As a single-hidden layer feedforward neural network, ELM has one hidden layer and one output layer. It has been proved that ELM provides better performance in classification and regression at shorter consumed time than some others, such as traditional support vector machine (SVM), without complex parameter adjustment. However, the weights of ELM hidden layer are randomly produced and the classification results of ELM are different because of this. To solve this problem, the kernel-based ELM was proposed, in which the hidden layer was processed with a kernel function to eliminate randomness. On the other hand, the Side-Scan Sonar images and the classified image data will be geo-referenced mosaicked using positions produced by extended Kalman filter (EKF) with sensor data from an autonomous underwater vehicle (AUV). To eliminate gaps in the mosaicking images, image dilation is adopted in our work. Experimental results demonstrate that the proposed classification method works well, and the proposed image mosaicking method is applicable when concerns real Side-Scan Sonar images.

  • Side-Scan Sonar image segmentation based on gray level co-occurrence matrices and unsupervised extreme learning machine
    OCEANS 2017 - Aberdeen, 2017
    Co-Authors: Yan Song, Guangliang Li, Chen Feng, Bo He
    Abstract:

    Side-Scan Sonar image segmentation is an important part in marine surveys, especially when we need to get the topographic features of the seabed. Actually, due to the complexity of the geomorphological characteristics in the seabed, we can't obtain any prior knowledge. Therefore we need an unsupervised system to segment Side-Scan Sonar images automatically. In this paper, a novel segmentation system for Side-Scan Sonar image based on Gray Level Co-occurrence Matrices (GLCM) and Unsupervised Extreme Learning Machine (US-ELM) is proposed. Experimental results demonstrate that the proposed method can get good segmentation.

  • Side-Scan Sonar image segmentation using Kernel-based Extreme Learning Machine
    2017 IEEE Underwater Technology (UT), 2017
    Co-Authors: Guoqing Ding, Guangliang Li, Yan Song, Chen Feng, Bo He
    Abstract:

    Autonomous Underwater Vehicles (AUVs) are important platform for oceanographic survey. AUVs have been widely applied to many fields, such as the ocean research, oil and gas exploitation, mineral resources investigation, fishing and military. People can obtain important ocean information by segmenting, classifying and recognizing Sonar image of AUV. So studying Side-Scan Sonar image is significant. Markov Random Field (MRF) is an efficient method for segmentation of Side-Scan Sonar image. However, MRF may not work well for Side-Scan Sonar image obtained from complex environment. In these images, pixel values do not change obviously. In this paper, an innovative segmentation method based MRF and Kernel-based Extreme Learning Machine (K-ELM) is proposed for real Side-Scan Sonar image segmentation. This method has been validated on the real Sonar images. Experimental results demonstrate that the proposed method outperforms MRF in classification accuracy.

  • Underwater object detection with efficient shadow-removal for Side Scan Sonar images
    OCEANS 2016 - Shanghai, 2016
    Co-Authors: Ruijie Chang, Bo He, Yaomin Wang, Rui Nian, Amaury Lendasse
    Abstract:

    Side Scan Sonar has been widely used in ocean investigations, underwater object detection by Side Scan Sonar is one of the most essential and fundamental tasks these years. In this paper, we present one simplified underwater object detection scheme with the help of shadow removal of Side Scan Sonar images. The fuzzy C-mean clustering (FCM) algorithm is first taken to partition all pixels from the Side Scan Sonar images into a collection of C fuzzy clusters, which makes shadow regions be segmented. The Criminisi algorithm based on isophote-driven image sampling process is then made full use of to undertake the shadow removal by filling the shadow region. Through the Otsu algorithm by choosing threshold value automatically, to segment the object and background we complete the object detection. It is shown from the simulation experiments that the proposed approach could achieve great performances in the object detection with both robustness and effectiveness.

Vera Van Lancker - One of the best experts on this subject based on the ideXlab platform.

  • Very-high resolution Side-Scan Sonar mapping of biogenic reefs of the tube-worm Lanice conchilega
    Remote Sensing of Environment, 2008
    Co-Authors: Steven Degraer, Geert Moerkerke, Gert Van Hoey, I Du Four, Jean-pierre Henriet, Marijn Rabaut, Magda Vincx, Vera Van Lancker
    Abstract:

    Reefs of the tube-building polychaete Lanice conchilega are known to represent hotspots of biodiversity within inter- and subtidal soft sediments of the North Sea. However, because of their patchy distribution, point sampling does not appropriately map their subtidal spatial distribution. This study evaluated the feasibility to detect L. conchilega reefs by very-high resolution Side-Scan Sonar imagery. A subtidal very-high resolution (410??kHz) Side-Scan survey, combined with grab sampling, revealed high densities of L. conchilega (up to 1979 ind. m- 2) to coincide with a higher reflectivity, patchy and grainy acoustic facies. From the Side-Scan Sonar imagery, individual reefs were estimated to reach a maximum size of 15??m2. To ground truth the acoustic facies, the distribution of intertidal L. conchilega reefs was mapped at low tide and Side-Scan Sonar imagery was recorded during the following high tide. Intertidal L. conchilega reefs had a patch size of 0.8??m2 up to 11.6??m2, elevated 7.5 to 11.5??cm above the surrounding seafloor and covered approximately 10% of the selected area. The very-high (445??kHz) resolution Side-Scan Sonar imagery revealed a similar acoustic facies as in the subtidal. Lower-resolution (132??kHz) Side-Scan Sonar imagery was less efficient to detect physically less developed L. conchilega reefs. We conclude that (1) there are no major technical restrictions to map L. conchilega reefs using Side-Scan Sonar, (2) the developmental stage of L. conchilega reefs impacts the detectability of the reefs, and (3) very-high resolution Side-Scan Sonar imagery is conSidered a necessity when mapping small-scale structures, such as L. conchilega reefs. ?? 2008 Elsevier Inc. All rights reserved.

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.

  • A Gray Scale Correction Method for Side-Scan Sonar Images Based on Retinex
    Remote Sensing, 2019
    Co-Authors: Xiufen Ye, Haibo Yang, Chuanlong Li, Peng Li
    Abstract:

    When Side-Scan Sonars collect data, Sonar energy attenuation, the residual of time varying gain, beam patterns, angular responses, and Sonar altitude variations occur, which lead to an uneven gray level in Side-Scan Sonar images. Therefore, gray scale correction is needed before further processing of Side-Scan Sonar images. In this paper, we introduce the causes of gray distortion in Side-Scan Sonar images and the commonly used optical and Side-Scan Sonar gray scale correction methods. As existing methods cannot effectively correct distortion, we propose a simple, yet effective gray scale correction method for Side-Scan Sonar images based on Retinex given the characteristics of Side-Scan Sonar images. Firstly, we smooth the original image and add a constant as an illumination map. Then, we divide the original image by the illumination map to produce the reflection map. Finally, we perform element-wise multiplication between the reflection map and a constant coefficient to produce the final enhanced image. Two different schemes are used to implement our algorithm. For gray scale correction of Side-Scan Sonar images, the proposed method is more effective than the latest similar methods based on the Retinex theory, and the proposed method is faster. Experiments prove the validity of the proposed method.

  • a feature matching method for Side Scan Sonar images based on nonlinear scale space
    Journal of Marine Science and Technology, 2016
    Co-Authors: Xiufen Ye, Peng Li, Jianguo Zhang
    Abstract:

    We report a novel feature-matching method for Side-Scan Sonar images. The method uses nonlinear diffusion filtering to build a nonlinear scale space. The noise-reduction performance is enhanced via nonlinear diffusion filtering, and the improved Perona–Malik diffusion equation results in a more distinct edge and line texture in the Side-Scan Sonar image. The modified feature descriptor reduces the dimensionality of the feature vector so that the computational expense is reduced. Experimental results show that the method provides improved noise-reduction performance and better accuracy than SIFT, SURF, and other state-of-the-art feature-matching algorithms.

  • ROBIO - A novel segmentation algorithm for Side-Scan Sonar imagery with multi-object
    2007 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2007
    Co-Authors: Xingmei Wang, Xiufen Ye, Huanran Wang, Lin Zhao, Kejun Wang
    Abstract:

    Automatic detection of underwater objects using Side-Scan Sonar imagery is complicated by the variability of objects, noises, and background signatures. In recent years, as the resolution of Side-Scan Sonar is much higher than before, the Sonar imagery can be generated from Sonar signal for processing. The first step of underwater object detection is to segment the underwater objects from Sonar imagery. In typical Sonar imagery, the object contains two parts: high-light areas (echo) and the shadow behind the object. By analyzing the features of the Side- Scan Sonar imagery, we propose a novel segmentation algorithm for multi-object Side-Scan Sonar imagery. First we utilize a self- adaptive window to Scan the imagery and calculate the variance of the window to segment the high-light areas in Sonar imagery. Then the shadows of the objects are segmented by fractal dimension. At last, the final segmentation results are achieved by combining the results from the above two steps for further analysis. This segmentation algorithm is based on analyzing the structure of objects in Sonar imagery and works well in the multi- object Sonar imagery.

  • A novel segmentation algorithm for Side-Scan Sonar imagery with multi-object
    2007 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2007
    Co-Authors: Xingmei Wang, Xiufen Ye, Huanran Wang, Lin Zhao, Kejun Wang
    Abstract:

    Automatic detection of underwater objects using Side-Scan Sonar imagery is complicated by the variability of objects, noises, and background signatures. In recent years, as the resolution of Side-Scan Sonar is much higher than before, the Sonar imagery can be generated from Sonar signal for processing. The first step of underwater object detection is to segment the underwater objects from Sonar imagery. In typical Sonar imagery, the object contains two parts: high-light areas (echo) and the shadow behind the object. By analyzing the features of the Side- Scan Sonar imagery, we propose a novel segmentation algorithm for multi-object Side-Scan Sonar imagery. First we utilize a self- adaptive window to Scan the imagery and calculate the variance of the window to segment the high-light areas in Sonar imagery. Then the shadows of the objects are segmented by fractal dimension. At last, the final segmentation results are achieved by combining the results from the above two steps for further analysis. This segmentation algorithm is based on analyzing the structure of objects in Sonar imagery and works well in the multi- object Sonar imagery.

Steven Degraer - One of the best experts on this subject based on the ideXlab platform.

  • Very-high resolution Side-Scan Sonar mapping of biogenic reefs of the tube-worm Lanice conchilega
    Remote Sensing of Environment, 2008
    Co-Authors: Steven Degraer, Geert Moerkerke, Gert Van Hoey, I Du Four, Jean-pierre Henriet, Marijn Rabaut, Magda Vincx, Vera Van Lancker
    Abstract:

    Reefs of the tube-building polychaete Lanice conchilega are known to represent hotspots of biodiversity within inter- and subtidal soft sediments of the North Sea. However, because of their patchy distribution, point sampling does not appropriately map their subtidal spatial distribution. This study evaluated the feasibility to detect L. conchilega reefs by very-high resolution Side-Scan Sonar imagery. A subtidal very-high resolution (410??kHz) Side-Scan survey, combined with grab sampling, revealed high densities of L. conchilega (up to 1979 ind. m- 2) to coincide with a higher reflectivity, patchy and grainy acoustic facies. From the Side-Scan Sonar imagery, individual reefs were estimated to reach a maximum size of 15??m2. To ground truth the acoustic facies, the distribution of intertidal L. conchilega reefs was mapped at low tide and Side-Scan Sonar imagery was recorded during the following high tide. Intertidal L. conchilega reefs had a patch size of 0.8??m2 up to 11.6??m2, elevated 7.5 to 11.5??cm above the surrounding seafloor and covered approximately 10% of the selected area. The very-high (445??kHz) resolution Side-Scan Sonar imagery revealed a similar acoustic facies as in the subtidal. Lower-resolution (132??kHz) Side-Scan Sonar imagery was less efficient to detect physically less developed L. conchilega reefs. We conclude that (1) there are no major technical restrictions to map L. conchilega reefs using Side-Scan Sonar, (2) the developmental stage of L. conchilega reefs impacts the detectability of the reefs, and (3) very-high resolution Side-Scan Sonar imagery is conSidered a necessity when mapping small-scale structures, such as L. conchilega reefs. ?? 2008 Elsevier Inc. All rights reserved.

Philipp Woock - One of the best experts on this subject based on the ideXlab platform.

  • Side-Scan Sonar simulation for a kernelized seafloor shape reconstruction approach
    2013 MTS IEEE OCEANS - Bergen, 2013
    Co-Authors: Philipp Woock
    Abstract:

    In this paper we show how an existing pixel-based surface elevation estimation method for Side-Scan Sonar data can be enhanced by using a kernelized surface representation. We discuss a Bayesian formulation for the Side-Scan imaging process and describe how methods of space carving and inverse ray tracing built on Markov Random Fields (MRF) can be introduced to the task of surface estimation from Side-Scan Sonar data.

  • deep sea seafloor shape reconstruction from Side Scan Sonar data for auv navigation
    OCEANS Conference, 2011
    Co-Authors: Philipp Woock
    Abstract:

    Dead-reckoning navigation in the deep sea is subject to errors due to accumulation of sensor inaccuracies. As no global referencing method exists for the deep sea like, e.g., GNSS (global navigation satellite system) for land or airborne vehicles other referencing solutions need to be employed. SLAM (Simultaneous Localization And Mapping) is a technique that exploits significant environmental features to reduce the positioning error of a vehicle and to simultaneously build a map of the mission environment. It is crucial for SLAM methods to recognize places that have been visited before. In many cases this is done by extracting salient features from the environment. Obtaining those landmarks from Side-Scan Sonar data is a challenging task as the Side-Scan Sonar data does not consist of spatial information but rather represents an echo amplitude over time. In Coiras et al. ([1], [2]) it is shown how a seafloor shape can be estimated from Side-Scan Sonar data by inversion and regularization. In this paper their method is extended to allow arbitrary vehicle motion. The results of the work will be presented in examples of synthetic and real data.

  • Side-Scan Sonar Based SLAM for the Deep Sea
    2010
    Co-Authors: Philipp Woock
    Abstract:

    In order to robustly perform SLAM (Simultaneous Localization and Mapping), places need to be recognized when they are visited again. In the deep-sea environment SLAM-assisted navigation based on Side-Scan Sonar data benefits from using three-dimensional features of the environment as they are much less view-dependent than classic 2D features. Obtaining these features requires processing of the Sonar data as the Side-Scan Sonar sensor readings contain three dimensional information only indirectly. To extract that information the ensonification process needs to be inverted. This inversion is an ill-posed inverse problem and therefore regularization is needed before a unique solution can be found. Once the true seabed shape is reconstructed, wide area SLAM techniques can be applied.