Sonar Image Segmentation Based on Multiscale Features in Contourlet Domain

doi:10.19678/j.issn.1000-3428.0054281

Computer Engineering ›› 2019, Vol. 45 ›› Issue (9): 253-259. doi: 10.19678/j.issn.1000-3428.0054281

Previous Articles Next Articles

Sonar Image Segmentation Based on Multiscale Features in Contourlet Domain

LI Peng^a,b, CHEN Jiaqi^a,b, MA Weimin^a,b, YE Fangyue^a,b

a. Jiangsu Key Laboratory of Meteorological Observation and Information Processing;b. Jiangsu Technology and Engineering Center of Meteorological Sensor Network, Nanjing University of Information Science and Technology, Nanjing 210044, China

Received:2019-03-18 Revised:2019-04-29 Online:2019-09-15 Published:2019-09-03

Contourlet域下基于多尺度特征的声呐图像分割

李鹏^a,b, 陈嘉琦^a,b, 马味敏^a,b, 叶方跃^a,b

南京信息工程大学 a. 江苏省气象探测与信息处理重点实验室;b. 江苏省气象传感网络技术工程中心, 南京 210044

作者简介:李鹏(1966-),男,教授、博士,主研方向为超声成像、图像处理;陈嘉琦、马味敏、叶方跃,硕士研究生。
基金资助:
国家自然科学基金（41075115）；江苏省重点研发计划社会发展项目（BE201569）；江苏省"六大人才高峰"第十一批高层次人才项目（2014-XXRJ-006）。

Abstract

Abstract: Complex and changeable underwater environment leads to the poor quality of sonar images,decreasing the accuracy of target recognition.Therefore,a level set sonar image segmentation algorithm based on multiscale Gaussian Markov Random Field(GMRF) model under Contourlet domain is proposed.Contourlet transform and inverse transform are used to obtain the texture feature under each scale layer of the sonar image.The texture feature of each layer is modeled by GMRF to describe the local structure spatial information and reduce the sensitivity to noise.Based on the texture feature models of each layer,coarse-to-fine segmentation for level sets is performed on sonar images to obtain segmentation results.Experimental results show that the accuracy of the algorithm exceeds 90% in different sonar images,which is better than Otsu algorithm and has lower complexity and stronger robustness.

Key words: Contourlet transform, Gauss Markov Random Field(GMRF)model, level set, sonar image segmentation, texture feature

摘要： 水下环境复杂多变，导致声呐技术成像后的图像质量差，影响目标识别。为此，提出一种基于Contourlet域下多尺度高斯马尔可夫随机场（GMRF）模型的水平集声呐图像分割算法。采用Contourlet变换及逆变换获取声呐图像各尺度层下的纹理特征，通过GMRF对各层纹理特征建模，以描述局部结构空间信息并降低对噪声的敏感度。根据各层纹理特征模型，对声呐图像进行由粗到细尺度的水平集分割以得到分割结果。实验结果表明，该算法在不同声呐图像中的分割准确度超过90%，优于Otsu算法，且具有较低的复杂度和较强的鲁棒性。

关键词: Contourlet变换, 高斯马尔科夫随机场模型, 水平集, 声呐图像分割, 纹理特征

CLC Number:

TP391

LI Peng, CHEN Jiaqi, MA Weimin, YE Fangyue. Sonar Image Segmentation Based on Multiscale Features in Contourlet Domain[J]. Computer Engineering, 2019, 45(9): 253-259.

李鹏, 陈嘉琦, 马味敏, 叶方跃. Contourlet域下基于多尺度特征的声呐图像分割[J]. 计算机工程, 2019, 45(9): 253-259.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0054281

http://www.ecice06.com/EN/Y2019/V45/I9/253

Figures/Tables 11

References

[1] 李海森,周天,徐超.多波束测深声纳技术研究新进展[J].声学技术,2013,32(2):73-80.
[2] LANGNER F,KNAUER C,JANS W,et al.Side scan sonar image resolution and automatic object detection,classification and identification[C]//Proceedings of OCEANS'09.Washington D.C.,USA:IEEE Press,2009:1-8.
[3] 朱玲羚.基于Otsu法的声呐图像多阈值分割方法[J].水雷战与舰船防护,2016,24(4):68-71,47.
[4] 李阳,庞永杰,盛明伟.结合空间信息的模糊聚类侧扫声纳图像分割[J].中国图象图形学报,2015,20(7):865-870.
[5] ASHRAF A B,GAVENONIS S C,DAYE D,et al.A multichannel Markov random field framework for tumor segmentation with an application to classification of gene expression-based breast cancer recurrence risk[J].IEEE Transactions on Medical Imaging,2013,32(4):637-648.
[6] 王雷,叶秀芬,王天.模糊聚类的侧扫声纳图像分割算法[J].华中科技大学学报(自然科学版),2012,40(9):25-29.
[7] SONG Sanming,SI Bailu,FENG Xisheng,et al.Label field initialization for MRF-based sonar image segmentation by selective autoencoding[C]//Proceedings of OCEANS'16.Washington D.C.,USA:IEEE Press,2016:1-5.
[8] SUN Ning,SHIM T,HAHN H.Sonar image segmentation based on Markov Gauss-Rayleigh mixture model[C]//Proceedings of International Workshop on Education Technology and International Workshop on Geoscience and Remote Sensing.Washington D.C.,USA:IEEE Computer Society,2008:704-709.
[9] SANG Enfang,SHEN Zhengyan,FAN Chang,et al.Sonar image segmentation based on implicit active contours[C]//Proceedings of IEEE International Conference on Intelligent Computing and Intelligent Systems.Washington D.C.,USA:IEEE Press,2009:228-231.
[10] LIU Guangyu,BIAN Hongyu,SHI Hong.Sonar image segmentation based on an improved level set method[J].Physics Procedia,2012,33:1168-1175.
[11] WANG Xingmei,GUO Longxiang,YIN Jingwei,et al.Narrowband Chan-Vese model of sonar image segmentation:a adaptive ladder initialization approach[J].Applied Acoustics,2016,113:238-254.
[12] LU Wen,ZENG Kai,TAO Dacheng,et al.No-reference image quality assessment in contourlet domain[J].Neurocomputing,2010,73(4/6):784-794.
[13] DO M N,VETTERLI M.The contourlet transform:an efficient directional multiresolution image representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[14] EMARY I M M E,RAMAKRISHNAN S.A critical review of statistical modeling of digital images[J].IAENG International Journal of Computer Science,2010,37(1):99-109.
[15] YANG Xi,GAO Xinbo,TAO Dacheng,et al.An efficient MRF embedded level set method for image segmentation[J].IEEE Transactions on Image Processing,2014,24(1):9-21.
[16] ONURAL L.Gibbs random fields and Markov random fields with constraints[EB/OL].[2019-02-15].https://arxiv.org/pdf/1603.01481.pdf.
[17] WANG Keqi,BAI Xuebing.Classification of wood surface texture based on Gauss-MRF model[J].Journal of Forestry Research,2006,17(1):57-61.
[18] YE Xiufen,ZHANG Zhehui,LIU P X,et al.Sonar image segmentation based on GMRF and level-set models[J].Ocean Engineering,2010,37(10):891-901.
[19] COHEN R.The Chan-Vese algorithm[J].Computer Science,2011,5(1):10-16.
[20] BÍLKOVÁ Z,SOUKUP J,KUERA V.Cell segmentation using level set methods with a new variance term[C]//Proceedings of International Conference on Image Analysis and Recognition.Berlin,Germany:Springer,2016:183-190.
[21] VANTARAM S R,SABER E.Survey of contemporary trends in color image segmentation[EB/OL].[2019-02-15].http://spie.org/Publications/Journal/10.1117/1.JEI.21.4.040901.

Please choose a citation manager

Content to export