联合NSCT与多重分形的高噪声侧扫声呐图像分割

doi:10.11947/j.AGCS.2020.20180276

摘要/Abstract

摘要： 针对现有分割算法对高噪声侧扫声呐图像分割准确率低的问题，提出了一种综合利用NSCT（non-subsampled contourlet transform）分解图像、局部标准差和均值组合增强图像和多重分形判断图像奇异性的侧扫声呐图像分割方法。首先，借助NSCT分解图像，获得滤除高频噪声且保留轮廓信息的低频图像和一系列高频方向子带图像。然后，基于侧扫声呐图像中目标及其阴影伴随出现的特点，计算低频图像的局部标准差与均值的组合特征，获得分别突显目标及其阴影的特征图，使用多重分形分割方法分割特征图，获得低频图像分割结果；利用图像差分和非极大值抑制方法分割高频方向子带图像，获得高频分割结果；融合高低频分割结果获得目标及其阴影的精细边缘。最后通过试验验证了本文方法的有效性。

关键词: 侧扫声呐, 图像分割, 组合特征, NSCT, 多重分形

Abstract: To improve the accuracy of current segmentation algorithms for the side scan sonar image with high noise, a side scan sonar image segmentation method is proposed that comprehensively utilizing of decomposing image by NSCT (non-subsampled contourlet transform), enhancing image by combination of local standard deviation and mean, estimating the singularity of image by multi-fractal. Firstly, NSCT is used to decompose images to obtain low frequency image which filtered out high frequency noise and retain contour information and a series of high-frequency direction sub-band images. Then, based on the feature that target shadow appeared with the target in side scan sonar images, it is calculated that the low-frequency image feature combined the local standard deviation and mean to obtain the feature images that highlight the characteristics of the target and its shadow respectively, use the multifractal method to segment the feature image to get the result of low-frequency image segmentation. The image difference and non-maximal suppression methods are used to segment the high-frequency direction sub-band images and obtain the high-frequency segmentation results. Finally, it is obtained that the fine edge of the target and its shadow by combing of high and low frequency segmentation result. The validity of this method is verified by experiments.

Key words: side-scan sonar, image segmentation, combined feature, NSCT, multifractal

中图分类号:

P229

何义才, 赵建虎, 张红梅, 阮世伦. 联合NSCT与多重分形的高噪声侧扫声呐图像分割[J]. 测绘学报, 2020, 49(2): 162-170.

HE Yicai, ZHAO Jianhu, ZHANG Hongmei, RUAN Shilun. Segmentation of polluted SSS image by combining NSCT and multifractal[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(2): 162-170.

参考文献

[1] CELIK T, TJAHJADI T. A novel method for sidescan sonar image segmentation[J]. IEEE Journal of Oceanic Engineering, 2011, 36(2):186-194.
[2] 赵建虎, 王晓, 张红梅, 等. 侧扫声呐图像分割的中性集合与量子粒子群算法[J]. 测绘学报, 2016, 45(8):935-942, 951. DOI:10.11947/j.AGCS.2016.20150555. ZHAO Jianhu, WANG Xiao, ZHANG Hongmei, et al. The neutrosophic set and quantum-behaved particle swarm optimization algorithm of side scan sonar image segmentation[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(8):935-942, 951. DOI:10.11947/j.AGCS.2016.20150555.
[3] 赵建虎. 现代海洋测绘[M]. 武汉:武汉大学出版社, 2007. ZHAO Jianhu. Modern marine surveying and charting[M]. Wuhan:Wuhan University Press, 2007.
[4] HUO Guanying, YANG S X, LI Qingwu, et al. A robust and fast method for sidescan sonar image segmentation using nonlocal despeckling and active contour model[J]. IEEE Transactions on Cybernetics, 2017, 47(4):855-872.
[5] 李擎, 唐欢, 迟健男, 等. 基于改进最大类间方差法的手势分割方法研究[J]. 自动化学报, 2017, 43(4):528-537. LI Qing, TANG Huan, CHI Jiannan, et al. Gesture segmentation with improved maximum between-cluster variance algorithm[J]. Acta Automatica Sinica, 2017, 43(4):528-537.
[6] 刘光宇, 卞红雨, 沈郑燕, 等. 基于声纳图像的水平集分割算法研究[J]. 传感器与微系统, 2012, 31(1):29-31. LIU Guangyu, BIAN Hongyu, SHENG Zhengyan, et al. Research on level set segmentation algorithm for sonar image[J]. Transducer and Microsystem Technologies, 2012, 31(1):29-31.
[7] 叶秀芬, 王兴梅, 张哲会, 等. 改进MRF参数模型的声呐图像分割方法[J]. 哈尔滨工程大学学报, 2009, 30(7):768-774. YE Xiufen, WANG Xingmei, ZHANG Zhehui, et al. Sonar imagery segmentation algorithm by improved MRF parameter model[J]. Journal of Harbin Engineering University, 2009, 30(7):768-774.
[8] 霍冠英, 刘静, 李庆武, 等. 空间约束FCM与MRF结合的侧扫声呐图像分割算法[J]. 仪器仪表学报, 2017, 38(1):226-235. HUO Guanying, LIU Jing, LI Qingwu, et al. Side-scan sonar image segmentation algorithm based on space-constrained FCM and MRF[J]. Chinese Journal of Scientific Instrument, 2017, 38(1):226-235.
[9] 沈郑燕. 声纳图像去噪与分割技术研究[D]. 哈尔滨:哈尔滨工程大学, 2010. SHEN Zhengyan. Research on techniques of sonar image de-noising and segmentation[D]. Harbin:Harbin Engineering University, 2010.
[10] 王雷. 侧扫声呐图像分割算法研究[D]. 哈尔滨:哈尔滨工程大学, 2013. WANG Lei. Research on the side-scan sonar image segmentation algorithm[D]. Harbin:Harbin Engineering University, 2013.
[11] 郭海涛, 田坦, 王连玉, 等. 利用二维属性直方图的最大熵的图像分割方法[J]. 光学学报, 2006, 26(4):506-509. GUO Haitao, TIAN Tan, WANG Lianyu, et al. Image segmentation using the maximum entropy of the two-dimensional bound histogram[J]. Acta Optica Sinica, 2006, 26(4):506-509.
[12] DA CUNHA A L, ZHOU J, DO M N. The nonsubsampled contourlet transform:theory, design, and applications[J]. IEEE Transactions on Image Processing, 2006, 15(10):3089-3101.
[13] 王倩, 彭海云, 秦杰, 等. NSCT域分类预处理的改进非局部均值去噪算法[J]. 计算机辅助设计与图形学学报, 2018, 30(3):436-446. WANG Qian, PENG Haiyun, QIN Jie, et al. Improved NLM denoising algorithm based on classification preprocess in NSCT domain[J]. Journal of Computer-Aided Design & Computer Graphics, 2018, 30(3):436-446.
[14] LI Q W, HUO G Y, LI H, et al. Special section on biologically-inspired radar and sonar systems-bionic vision-based synthetic aperture radar image edge detection method in non-subsampled contourlet transform domain[J]. IET Radar, Sonar & Navigation, 2012, 6(6):526-535.
[15] 李庆武, 马国翠, 霍冠英, 等. 基于NSCT域边缘检测的侧扫声呐图像分割新方法[J]. 仪器仪表学报, 2013, 34(8):1795-1801. LI Qinwu, MA Guocui, HUO Guanying, et al. New segmentation method of side-scan sonar image based on edge detection in NSCT domain[J]. Chinese Journal of Scientific Instrument, 2013, 34(8):1795-1801.
[16] 杨旭朗, 侯榆青, 陈燊, 等. 一种基于图像灰度和方差信息的图像分割方法[J]. 量子电子学报, 2010, 27(6):677-682. YANG Xulang, HOU Yuqing, CHEN Shen, et al. An image segmenting method based on image gray and variance information[J]. Chinese Journal of Quantum Electronics, 2010, 27(6):677-682.
[17] NAYAK S R, RANGANATH A, MISHRA J. Analysing fractal dimension of color images[C]//Proceedings of 2015 International Conference on Computational Intelligence and Networks. Bhubaneshwar:IEEE, 2015:156-159.
[18] SHI Wen, ZOU Ruibiao, WANG Fang, et al. A new image segmentation method based on multifractal detrended moving average analysis[J]. Physica A:Statistical Mechanics and Its Applications, 2015, 432(8):197-205.
[19] PASKAŠ M P, RELJIN B D, RELJIN I S. Multifractal techniques for texture classification and image filtering[C]//Proceedings of the 23rd Telecommunications Forum Telfor. Belgrade:IEEE, 2015:791-798.
[20] 岳春宇, 江万寿. 基于最大后验和非局域约束的非下采样轮廓波变换域SAR图像去噪方法[J]. 测绘学报, 2012, 41(1):59-64. YUE Chunyu, JIANG Wanshou. An algorithm of SAR image denoising in nonsubsampled contourlet transform domain based on maximum a posteriori and non-local restriction[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(1):59-64.
[21] ZHANG Qiong, MALDAGUE X. An adaptive fusion approach for infrared and visible images based on NSCT and compressed sensing[J]. Infrared Physics & Technology, 2016, 74(1):11-20.
[22] GHAZ A, KPALMA K, BOUNOUA A. NSCT edge enhancement for SIFT key points extraction[J]. IOSR Journal of VLSI and Signal Processing, 2014, 4(2):84-90.
[23] 傅鹏, 孙权森, 纪则轩. 结合分形理论和自适应图像块划分的遥感图像噪声估计[J]. 测绘学报, 2015, 44(11):1235-1245. FU Peng, SUN Quansen, JI Zexuan. Noise estimation from remote sensing images by fractal theory and adaptive image block division[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(11):1235-1245.
[24] CHAUVEAU J, ROUSSEAU D, RICHARD P, et al. Multifractal analysis of three-dimensional histogram from color images[J]. Chaos, Solitons & Fractals, 2010, 43(1-12):57-67.
[25] COMBREXELLE S, WENDT H, DOBIGEON N, et al. Bayesian estimation of the multifractality parameter for image texture using a whittle approximation[J]. IEEE Transactions on Image Processing, 2015, 24(8):2540-2551.
[26] NI Haiming, QI Dawei, MU Hongbo. Edge detection of the Siberian tiger skull CT image by multifractal spectrum theory[C]//Proceedings of the International Coference on Advanced Science and Technology 2016. Haikou:[s.n.]2016:270-273.
[27] 赵健, 雷蕾, 蒲小勤. 分形理论及其在信号处理中的应用[M]. 北京:清华大学出版社, 2008. ZHAO Jian, LEI Lei, PU Xiaoqin. Fractal theory and its application in signal processing[M]. Beijing:Tsinghua University Press, 2008.
[28] 冯昌利, 张建勋, 梁睿, 等. 基于分形几何和最小凸包法的肺区域分割算法[J]. 天津大学学报(自然科学与工程技术版), 2015, 48(10):937-946. FENG Changli, ZHANG Jianxun, LIANG Rui, et al. A lung region segmentation method based on the fractal theory and the minimal convex hull method[J]. Journal of Tianjin University (Science and Technology), 2015, 48(10):937-946.
[29] NILSSON E. Multifractal-based image analysis with applications in medical imaging[D]. Sweden:Umeå University, 2007:1-76.
[30] ALRAWI A T, SAGHEER A M, IBRAHIM D A. Texture segmentation based on multifractal dimension[J]. International Journal of Soft Computing, 2012, 3(1):1-10. DOI:10.5121/ijsc.2012.3101.
[31] BUCUR D, MAZZOLENI D, PRATELLI A, et al. Lipschitz regularity of the eigenfunctions on optimal domains[J]. Archive for Rational Mechanics and Analysis, 2015, 216(1):117-151.
[32] DAMERVAL C, MEIGNEN S. Study of a robust feature:the pointwise Lipschitz regularity[J]. International Journal of Computer Vision, 2010, 88(3):363-381.
[33] YURI. Air France 447:buscando cajas negras a 4.000 metros de profundidad (y2)[EB/OL]. (2014-03-14). http://www.lapizarradeyuri.com/2014/03/10/air-france-447-buscando-cajas-negras-a-4-000-metros-de-profundidad-y-2/.
[34] EdgeTech. Image Scans Gallery[EB/OL].[2017-12-06] https://www.edgetech.com/underwater-technology-gallery/.