基于复无下采样轮廓波和Gaussian小波支持向量回归的红外目标图像背景抑制

doi:10.3969/j.issn.1000-1093.2015.04.017

摘要/Abstract

摘要： 针对存在背景干扰和噪声情况下的红外目标图像背景抑制问题，提出了一种基于复无下采样轮廓波变换（NSCCT）和Gaussian小波支持向量回归（SVR）的背景抑制方法。该方法对红外目标图像进行NSCCT，然后根据其系数的相关特性去噪，从而抑制了大部分背景杂波；采用Gaussian小波SVR对去噪后的红外目标图像进行处理得到预测图像，并用去噪后图像减去预测图像得到残差图像，即背景抑制结果。针对红外目标图像进行了大量实验，并与近年来提出的3种背景预测方法，即基于最小二乘支持向量回归（LS-SVR）、基于SVR及基于最小二乘的红外目标图像背景抑制方法进行了比较，结果表明所提出的方法去噪效果好，背景抑制性能更优。针对存在背景干扰和噪声情况下的红外目标图像背景抑制问题，提出了一种基于复无下采样轮廓波变换（NSCCT）和Gaussian小波支持向量回归（SVR）的背景抑制方法。该方法对红外目标图像进行NSCCT，然后根据其系数的相关特性去噪，从而抑制了大部分背景杂波；采用Gaussian小波SVR对去噪后的红外目标图像进行处理得到预测图像，并用去噪后图像减去预测图像得到残差图像，即背景抑制结果。针对红外目标图像进行了大量实验，并与近年来提出的3种背景预测方法，即基于最小二乘支持向量回归（LS-SVR）、基于SVR及基于最小二乘的红外目标图像背景抑制方法进行了比较，结果表明所提出的方法去噪效果好，背景抑制性能更优。

关键词: 信息处理技术, 红外搜索与跟踪, 弱小目标检测, 背景抑制, 复无下采样轮廓波变换, Gaussian小波支持向量回归

Abstract: For the background suppression problem of dim target infrared image that contains background interference and noise, a new background suppression method based on nonsubsampled complex contourlet transform (NSCCT) and Gaussian wavelet support vector regression (SVR) is presented. With this method, the nonsubsampled complex contourlet transform is performed for the infrared target image, and then the correlation properties of NSCCT coefficients are used to de-noise the image so that the majority of background clutter is suppressed. Gaussian wavelet support vector regression is used to process the denoised infrared image to obtain the predicted image. The predicted image subtracted from the denoised image gives the residual image and the background is suppressed. A large number of experiments are done on infrared images including small targets, and the comparison is made with the background suppression methods of infrared target image based on least squares support vector regression, support vector regression and least squares. The experimental results show that the suggested method can get better de-noising result, and the performance of background suppression is superior.

Key words: information processing technology, infrared search and track, infrared dim target detection, background suppression, nonsubsampled complex contourlet transform, Gaussian wavelet support vector regression

中图分类号:

TN219

吴一全，宋昱. 基于复无下采样轮廓波和Gaussian小波支持向量回归的红外目标图像背景抑制[J]. 兵工学报, 2015, 36(4): 687-695.

WU Yi-quan， SONG Yu. Background Suppression of Small Infrared Target Image Based on Nonsubsampled Complex Contourlet Transform and GaussianWavelet Support Vector Regression[J]. Acta Armamentarii, 2015, 36(4): 687-695.

参考文献

［1］ Zhu F Y，Qin S Y. A moving IR point target detection algorithm based on reverse phase feature of neighborhood in difference between neighbor frame images［J］. Chinese Journal of Aeronautics, 2006, 9(3): 225-232.
［2］ Zhang T X，Li M，Zuo Z R， et al. Moving dim point target detection with three-dimensional wide-to-exact search directional filtering［J］. Pattern Recognition Letters，2007，28(2)：246-253.
［3］陈炳文, 王文伟, 秦前清. 基于分数阶积分算子的红外弱小目标检测［J］. 控制与决策, 2012, 27(1): 147-151.
CHEN Bing-wen, WANG Wen-wei, QIN Qian-qing. Infrared dim target detection based on fractional integral operator［J］. Control and Decision, 2012, 27(1)：147-151. (in Chinese)
［4］曹琦, 毕笃彦. 红外弱小目标检测中的特征选择性滤波方法［J］. 光学学报, 2009, 29(9): 2408-2412.
CAO Qi, BI Du-yan. Characteristic-selecting filtering in infrared small target detection［J］. Acta Optica Sinica，2009, 29(9): 2048-2412. (in Chinese)
［5］靳永亮, 王延杰, 刘艳滢, 等. 红外弱小目标的分割预检测［J］. 光学精密工程, 2012, 20(1): 171-178.
JIN Yong-liang, WANG Yan-jie, LIU Yan-ying, et al. Pre-detection method for small infrared target［J］. Optics and Precision Engineering, 2012, 20(1): 171-178. (in Chinese)
［6］罗寰, 王芳, 陈中起，等. 基于对称差分和光流估计的红外弱小目标检测［J］. 光学学报, 2010, 30(6): 1715-1810.
LUO Huan, WANG Fang, CHEN Zhong-qi, et al. Infrared target detecting based on symmetrical displaced frame difference and optical flow estimation［J］. Acta Optica Sinica, 2010, 30(6): 1715-1810. (in Chinese)
［7］ Xu Y S, Weaver J B, Healy D M. Wavelet transform domain filters: a spatially selective noise filtration technique［J］. IEEE Transactions on Image Processing，1994, 3(6): 747-758.
［8］ Mallat S, Hwang W L. Singularity detection and processing with wavelets［J］. IEEE Transactions on Information Theory, 1992, 38(2): 617-643.
［9］ Zhang L, Bao P, Pan Q. Threshold analysis in wavelet-based de-noising［J］. IEEE Electronics Letters，2001, 37(24): 1485-1486.
［10］ Candès E J. Ridgelets: theory and applications［D］. California: Stanford University, 1998.
［11］ Candes E J, Donoho D L. Curvelets-a surprisingly effective non-adaptive representation for objects with edges［R］. Palo Alto, California: Stanford University，1999.
［12］ Minh N D, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation［J］. IEEE Transactions on Image Processing, 2005, 14(12): 2091-2106.
［13］ Selesnick I W, Baraniuk R G, Kingsbury N C. The dual-tree complex wavelet transform［J］. IEEE Signal Processing Magazine, 2005, 22(6): 123-151.
［14］ Arthur L C, Zhou J P, Minh N D. The nonsubsampled contourlet transform: theory, design, and applications［J］. IEEE Transactions on Image Processing, 2006, 15(10)：3089-3101.
［15］ Guo K H, Kutyniol G, Labate D. Sparse multidimensional representations using anisotropic dilation and shear operators［C］∥International Conference on the Interaction between Wavelets and Splines. Athens, GA: Nashboro Press, 2005: 189-201.
［16］秦翰林, 李佳, 周慧鑫, 等. 采用剪切波变换的红外弱小目标背景抑制［J］. 红外与毫米波学报, 2011，30(2)：162-166.
QIN Han-lin, LI Jia, ZHOU Hui-xin, et al. Infrared dim and small target background suppression using shearlet transform［J］. Journal of Infrared Millimeter Waves, 2011, 30(2): 162-166. (in Chinese)
［17］王咏胜, 付永庆. 非抽样复Contourlet变换的构造及其图像去噪应用［J］. 大连海事大学学报, 2009, 35(2)：76-80.
WANG Yong-sheng, FU Yong-qing. Construction of nonsubsampled complex contourlet transform and its application to image denoising［J］. Journal of Dalian Maritime University, 2009, 35(2): 76-80. (in Chinese)
［18］陈新武, 龚均斌, 刘玮, 等. 基于复轮廓波变换的图像消噪［J］. 光电工程, 2009, 36(10): 111-115.
CHEN Xin-wu, GONG Jun-bin, LIU Wei, et al. Image denoising based complex contourlet transform［J］. Opto-Electronic Engineering, 2009, 36(10):111-115. (in Chinese)
［19］王咏胜, 付永庆. 基于非抽样复轮廓波变换的图像去噪算法研究［J］. 光电子·激光, 2009, 20(8): 1118-1122.
WANG Yong-sheng, FU Yong-qing. Study of image denoising based on nonsubsampled complex contourlet transform［J］. Journal of Optoelectronics, 2009, 20(8): 1118-1122. (in Chinese)
［20］秦翰林, 姚柯柯, 周慧鑫, 等. 基于塔型对偶树方向滤波器组的弱小目标背景抑制方法［J］. 兵工学报, 2012, 33(9): 1036-1040.
QIN Han-lin, YAO Ke-ke, ZHOU Hui-xin, et al. Background suppression for dim and small targets based on pyramidal dual-tree directional filter bank［J］. Acta Armamentarii，2012, 33(9): 1036-1040. (in Chinese)
［21］焦建彬, 杨舒, 刘峰, 等. 基于人工神经网络的红外小目标检测［J］. 控制工程, 2010, 17(5): 611-613.
JIAO Jian-bin, YANG Shu, LIU Feng, et al. Small infrared target detection based on artificial neural network［J］. Control Engineering of China, 2010, 17(5): 611-613. (in Chinese)
［22］ Corinna C, Vladimir V. Support-vector networks［J］. Machine-Learning，1995，20(3)：273-297.
［23］ Lin Y, Zhang S M, Cai J Q, et al. Application of wavelet support vector regression on SAR data de-noising［J］. Journal of Systems Engineering and Electronics, 2011, 22(4): 579-586.
［24］荣健, 申金娥, 钟晓春. 基于小波和SVR的红外弱小目标检测方法［J］. 西南交通大学学报, 2008, 43(5)：556-560.
RONG Jian, SHEN Jin-e, ZHONG Xiao-chun. New method for infrared dim target detection based on wavelet and SVR［J］. Journal of Southwest Jiaotong University, 2008, 43(5)：556-560. (in Chinese)
［25］于振华, 蔡远利. 基于在线小波支持向量机回归的混沌时间序列预测［J］. 物理学报, 2006，55(4)：1660-1664.
YU Zhen-hua， CAI Yuan-li. Prediction of chaotic time-series based on online wavelet support vector regression［J］. Acta Physica Sinica，2006，55(4)：1660-1664. (in Chinese)
［26］ Zhang S M, Chen Y. Image denoising based on wavelet support vector regression［J］. Machine Graphics and Vision, 2006, 15(3/4): 673-680.
［27］杨帆, 赵瑞珍, 胡绍海. 基于Contourlet系数相关特性的自适应图像去噪算法［J］. 光学学报, 2009, 29(2): 357-361.
YANG Fan, ZHAO Rui-zhen, HU Shao-hai. Adaptive algorithm for image denoising based on correlation properties of contourlet coefficients［J］. Acta Optica Sinica, 2009, 29(2): 357-361. (in Chinese)

[1]	曾溢良，蓝金辉，邹金霖. 滑动置信度约束的红外弱小目标跟踪算法研究[J]. 兵工学报, 2017, 38(9): 1771-1778.
[2]	李关防，崔杰，袁富宇. 基于线谱瞬时频率估计的被动声纳目标运动分析[J]. 兵工学报, 2017, 38(7): 1395-1401.
[3]	朱甦，薄煜明，何亮. 基于冗余字典的多特征压缩感知目标跟踪算法[J]. 兵工学报, 2017, 38(6): 1140-1146.
[4]	王啸, 韩太林, 张永立, 刘轩, 王义君, 宫玉琳. 多通道瞬态信号自适应变频算法[J]. 兵工学报, 2017, 38(6): 1161-1167.
[5]	张石，张百海，王飞帆，关子霄. 基于跳数量化的无线传感器网络节点定位算法[J]. 兵工学报, 2017, 38(5): 932-939.
[6]	夏平, 任强, 吴涛, 雷帮军. 融合多尺度统计信息模糊C均值聚类与Markov随机场的小波域声纳图像分割[J]. 兵工学报, 2017, 38(5): 940-948.
[7]	曹俊，郑翠娥，孙大军，张殿伦. 基于凸优化的水下载体定位研究[J]. 兵工学报, 2017, 38(3): 520-526.
[8]	向颉，茅永兴，郭才发. 船载雷达测速数据的船速修正新方法[J]. 兵工学报, 2017, 38(11): 2268-2273.
[9]	潘江怀，乔慧. 多传感器空间配准的病态性及其稳健估计[J]. 兵工学报, 2017, 38(10): 1965-1973.
[10]	王清，丁赤飚，付琨，任文娟. 基于膨胀运算的移动对象兴趣点检测方法[J]. 兵工学报, 2017, 38(10): 2041-2047.
[11]	李子高，李淑秋，闻疏琳. 一种基于独立成分分析的水下宽带信号波达方位估计方法[J]. 兵工学报, 2017, 38(1): 114-122.
[12]	刘泳庆，蒋硕，于栋，邵晓田. 窄带干扰抑制对码相位测量零值的影响分析[J]. 兵工学报, 2016, 37(2): 293-298.
[13]	管四海, 李智，黄辉，王哲. 带零吸收项的变步长l₀范数归一化最小均方误差算法[J]. 兵工学报, 2016, 37(11): 2170-2176.
[14]	焦传海，李永成，谢恺，杨运甫. 基于期望偏差和广义似然比检验的非重构宽带压缩盲感知[J]. 兵工学报, 2016, 37(10): 1837-1843.
[15]	刘红，曹颖，隆腾舞. 基于改进离散粒子群优化算法的容差电路故障特征提取[J]. 兵工学报, 2015, 36(8): 1494-1501.