基于改进的剪切波变换和引导滤波的红外弱小目标背景抑制方法

荣生辉; 刘刚; 周慧鑫; 秦翰林; 钱琨; 延翔; 赵东

doi:doi:10.3788/gzxb20154402.0210002

光子学报, 2015, 44 (2): 0210002, 网络出版: 2015-02-15

基于改进的剪切波变换和引导滤波的红外弱小目标背景抑制方法

Infrared Dim and Small Target Background Suppression Based on the Improved Shearlet Transformand the Guide Filter

论文大纲

荣生辉 ^1,*刘刚 ²周慧鑫 ¹秦翰林 ¹钱琨 ¹延翔 ¹赵东 ¹

作者单位

¹ 西安电子科技大学物理与光电工程学院, 西安 710071

² 上海卫星工程研究所, 上海 200240

摘要

由于传统的背景抑制方法没有充分利用信号的方向信息, 使其不能有效区分背景边缘和红外弱小目标, 从而造成背景抑制结果中有较多的背景泄露.针对上述问题, 本文利用改进的剪切波变换和引导滤波, 提出了一种新的背景抑制方法.首先,采用改进的剪切波变换对红外弱小目标图像进行多尺度和多方向分解, 将图像分解得到不同的高频子带系数和低频子带系数;其次, 利用目标信号与边缘在方向上的差异, 采用自适应引导滤波对高频子带系数进行处理;再次, 对分解后的低频子带系数和处理后的高频子带系数进行改进的剪切波逆变换, 得到预测的背景图像;最后, 将原图像与背景预测图像相减获得背景抑制且目标增强的红外图像.为了验证本文方法的有效性, 采用多组实验对其进行验证, 并与经典的Max-Median、TDLMS和Top-hat等方法作比较.多组实验结果均表明本文方法在主观视觉和客观评价指标方面均优于其它三种经典方法, 可有效提高红外搜索跟踪系统对红外弱小目标的探测概率.

Abstract

Because traditional background suppression methods don't take full advantage of direction information, small target and edges can't be distinguished effectively and some background may expose. A new method based on improved shearlet transform and image guide filter was proposed. Firstly, nonsubsampled wavelet transform and shear directional filter bank is adopted to decompose the infrared image into multi-scale and multi-direction to obtain high frequency and low frequency coefficients. Then the image guide filter is used to adjust the high frequency coefficients of each sub-bands to suppress the dim and small target signal and predict the background. Then the estimated background is obtained by the inverse transformation. At last, the suppression result is obtained by subtracting the estimated bcakground from the original image. Several group of experimental results demonstrate that the presented method can suppress the background and enhance the small target signal effectively, compared with several classical methods, such as Max-Median、TDLMS and Top-hat. The proposed method can effectively improve the detection probability of infrared search and tracking system for infrared dim and small target.

参考文献

[1] BAI X Z, ZHOU F G. Analysis of new top-hat transformation and the application for infrared dim small target detection［J］.Pattern Recognition, 2010, 43(6): 2145-2156.

[2] BAE T W, KIM Y C, AHN S H,et al. An efficient two-dimensional least mean square (TDLMS) based on block statistics for small target detection［J］.Journal of Infrared Millimeter and Terahertz Wave, 2009, 30: 1099-1101.

[3] DESHPANDE S D, ER M H, VENKATESWARLU R, et al. Max-mean and max-median filters for detection of small targets［C］.SPIE, 1999, 3809: 71 - 83.

[4] GAO C, DEYU M, YANG Y, et al. Infrared patch-image model for small target detection in a single image［J］.IEEE Transactions on Image Processing, 2013, 22(12): 4996-5009.

[5] 王卫华, 牛照东, 陈曾平. 基于时空域融合滤波的红外运动小目标检测方法［J］.红外与激光工程, 2006, 34(6): 714-718.

WANG Wei-hua, NIU Zhao-dong, CHEN Zeng-ping. Temporal spatial fusion filtering algorithm for small infrared moving target detection［J］.Infrared and Laser Engineering, 2006, 34(6): 714 -718.

[6] 廖斌, 杨卫平. 基于多帧移位叠加的红外小目标检测方法［J］.红外与激光工程, 2002, 31(2): 150-153.

LIAO Bin, YANG Wei-ping, SHEN Zhen-kang. Dim target detection algorithm based on multi frame indexing accumulation［J］.Infrared and Laser Engineering, 2002, 31(2): 150-153.

[7] BAE T W, KIM B I, KIM Y C, et al. Small target detection using cross product based on temporal profile in infrared image sequences［J］.Computers & Electrical Engineering, 2010, 36(6): 1156-1164.

[8] DELMARCO S, AGAIAN S. The design of wavelets for image enhancement and target detection［C］．SPIE, 2009, 735103: 1-12.

[9] 陈方涵, 王文生, 杨坤等. 基于多小波变换的红外目标探测与识别［J］.光子学报,2011,40(2): 295-298.

CHEN Fang-han, WANG Wen-sheng, YANG Kun, et al. Detection and recognition of infrared target based on the multiwavelet transform［J］.Acta Photonica Sinica, 2011, 40(2): 295-298.

[10] 秦翰林, 刘上乾, 周慧鑫, 等. 采用Gabor核非局部均值的弱小目标背景抑制［J］.红外与激光工程, 2009, 38(4): 737-741.

QIN Han-lin, LIU Shang-qian, ZHOU Hui-xin, et al. Background suppression for dim small target with Gabor kernel nonlocal means ［J］.Infrared and Laser Engineering, 2009, 38(4): 737-741.

[11] GUO K, DEMETRIO L. Optimally sparse multidimensional representation using Shearlets［J］.SIAM Journal on Mathematical Analysis, 2007, 39(1): 298-318.

[12] LIMW Q. The discrete Shearlets transform: A new directional transform and compactly supported Shearlets frames［J］.IEEE Transactions on Image Processing, 2010, 19(5): 1166-1180.

[13] GLENN E, DEMETRIO L, LIM W Q. Sparse directional image representations using the discrete shearlet transform［J］.Applied and Computational Harmonic Analysis, 2008, 25(1): 25-46.

[14] HE K, SUN J, TANG X. Guided image filtering［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.

[15] KIM S, LEE J. Scale invariant small target detection by optimizing signal-to-clutter ratio in heterogeneous background for infrared search and track［J］.Pattern Recognition, 2012, 45(1): 393-406.

[16] GAO C, ZHANG T, LI Q. Small infrared target detection using sparse ring representation［J］.Aerospace and Electronic Systems Magazine, 2012, 27(3): 21-30.

[17] 崔璇, 辛云宏. 一种有效的红外小目标检测方法［J］.光子学报, 2014,43(2): 2100031-02100035.

CUI Xuan, XIA Yun-hong. An effective method in the detection of infrared dim target［J］.Acta Photonica Sinica, 2014, 43(2): 2100031-02100035.

[18] 薛松, 韩广良. 基于局部峰值的红外弱小目标快速检测［J］.光子学报, 2013,42(2): 228-233.

XUE Song, HAN Guang-ling. Infrared small target fast detection based on local saliency［J］.Acta Photonica Sinica, 2013, 42(2): 228-233.

[19] 秦翰林, 韦桂锋, 周慧鑫,等. 采用视觉细胞响应模型的小目标复杂背景抑制［J］.光子学报, 2011,40(9): 1423-1427.

QIN Han-lin, WEI Gui-feng, ZHOU Hui-xin, et al. Vision cell response model for small target complex background suppression［J］.Acta Photonica Sinica, 2011, 40(9): 1423-1427.

荣生辉, 刘刚, 周慧鑫, 秦翰林, 钱琨, 延翔, 赵东. 基于改进的剪切波变换和引导滤波的红外弱小目标背景抑制方法[J]. 光子学报, 2015, 44(2): 0210002. RONG Sheng-hui, LIU Gang, ZHOU Hui-xin, QIN Han-lin, QIAN Kun, YAN Xiang, ZHAO Dong. Infrared Dim and Small Target Background Suppression Based on the Improved Shearlet Transformand the Guide Filter[J]. ACTA PHOTONICA SINICA, 2015, 44(2): 0210002.

基于改进的剪切波变换和引导滤波的红外弱小目标背景抑制方法

关于本站 Cookie 的使用提示

全站搜索

基于改进的剪切波变换和引导滤波的红外弱小目标背景抑制方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索