结合统计分布和非下采样Contourlet 变换的红外小目标检测

刘兴淼; 王仕成; 赵静

doi:10.3788/OPE.20111904.0908

您当前的位置：

首页 >

文章列表页 >

结合统计分布和非下采样Contourlet 变换的红外小目标检测

信息科学 | 更新时间：2020-08-12

- 结合统计分布和非下采样Contourlet 变换的红外小目标检测
- Infrared small target detection based on nonsubsampled Contourlet transform and statistical distribution
- 光学精密工程 2011年19卷第4期页码：908-915
- 作者机构：
  
  第二炮兵工程学院,陕西西安 710025
- 作者简介：
- 基金信息：
  
  某院重点平台建设项目(No. WX07233)()
- DOI：10.3788/OPE.20111904.0908
  中图分类号： TP391.4
- 收稿日期：2010-05-14，
  
  修回日期：2010-07-07，
  
  网络出版日期：2011-04-26，
  
  纸质出版日期：2011-04-26
- 稿件说明：
移动端阅览
刘兴淼, 王仕成, 赵静. 结合统计分布和非下采样Contourlet 变换的红外小目标检测[J]. 光学精密工程, 2011,19(4): 908-915

LIU Xing-miao, WANG Shi-cheng, ZHAO Jing. Infrared small target detection based on nonsubsampled Contourlet transform and statistical distribution[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 908-915
刘兴淼, 王仕成, 赵静. 结合统计分布和非下采样Contourlet 变换的红外小目标检测[J]. 光学精密工程, 2011,19(4): 908-915 DOI： 10.3788/OPE.20111904.0908.

LIU Xing-miao, WANG Shi-cheng, ZHAO Jing. Infrared small target detection based on nonsubsampled Contourlet transform and statistical distribution[J]. Editorial Office of Optics and Precision Engineering, 2011,19(4): 908-915 DOI： 10.3788/OPE.20111904.0908.

摘要

在分析存在背景和噪声干扰下的红外小目标检测方法的基础上

提出了一种时空结合的红外小目标检测算法。首先

基于相邻帧背景图像灰度值变化的特点

提出了基于三阶中心矩统计分布确定小目标区域方法

接着对图像进行非下采样Contourlet变换(NSCT)

定义子带的能量系数

并结合各个子带的能量系数得到各点的能量值

进而得到一个基于各点能量值的图像。最后

根据能量图像中小目标、背景及噪声的不同分布特点

利用阈值分割得到要检测的小目标。仿真实验结果表明

该方法能较精确地检测出红外小目标

具有较高的检测率和较小的平均虚警数;对单一背景和运动背景下的红外小目标进行检测

其检测率分别达到了98%和97%

平均虚警数仅为0.05和0.17

并且在小目标出现快速以及不规则运动时仍能进行有效检测。

Abstract

The method to detect small moving targets in infrared image sequences that contain moving nuisance objects and background noises is analyzed in this paper. An infrared small target detection algorithm combined with temporal and spatial domains is put forward. On the basis of the background change slowly

the algorithm firstly confirms the object region based on the third central moments of frame difference

and decomposes the frame difference image by nonsubsampled Contourlet transform to define the energy coefficients of the sub-band images. Then the image based on the energy value of each pixel is obtained. Finally

the final detecting of the target is realised according to the different features of small targets

backgrounds and noises. The results indicate that the small infrared target detection based on nonsubsampled Contourlet transform can precisely detect the small infrared target and has better target detection performance. When the small targets with invariable and moving backgrounds are detected

the detection rate of the proposed algorithm can reach 98% and 97% and the mean of false alarm points is only 0.05 and 0.17

respectively.It concludes that the proposed algorithm can detect the small target when the target has fast or anomalistic movement.

关键词

Keywords

references

吴文怡,吴一全. 基于Contourlet变换的红外弱小目标检测方法[J]. 红外与激光工程, 2008,37(1):136-138. WU W Y, WU Y Q. Method of infrared dim targets detection based on Contourlet transform[J].Infrared and Laser Engineering, 2008,37(1):136-138.(in Chinese)[2] BARNETT J. Statistical analysis of median subtraction filtering with application to point target detection in infrared backgrounds[J]. SPIE,1989,1050:10-18.[3] TOM V T,PELI T,LEUNG M.Morpholo-gybased algorithm for point-target detection in infrared backgrounds[J]. SPIE, 1993,1954:2-11.[4] DO M N,VETTERLI M. Contourlets: a directional multiresolution image representation . IEEE Int. Conf on Image Processing, Rochester,September,2002,1:357-360.[5] CUNHA L D,ZHOU J P,DO M N. The nonsubsampled Contourlet transform: theory design and applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.[6] 吴一全,罗子娟,吴文怡. 基于NSCT的红外图像小目标检测技术[J]. 中国图象图形学报, 2009,14(3):477-481. WU Y Q, LUO Z J, WU W Y. A method of small target detection in infrared image based on nonsubsampled contourlet transforms[J]. Journal of Image and Graphics, 2009,14(3):477-481. (in Chinese)[7] 高陈强,田金文,王鹏. 基于时域特性分析的红外运动小目标检测算法[J]. 红外与激光工程, 2008,37(5):907-910. GAO CH Q, TIAN J W, WANG P. Detection algorithm for infrared moving small target based on temporal domain characteristics analysis[J]. Infrared and Laser Engineering, 2008,37(5):907-910. (in Chinese)[8] 赵晶晶, 谌海新,刘星彤. 能量累积与均值漂移聚类结合的红外小目标检测方法[J]. 中国图象图形学报,2008,13(10):1878-1881. ZHAO J J, CHEN H X, LIU X T. Small target detection based on method energy accumulation [J]. Journal of Image and Graphics, 2008,13(10):1878-1881. (in Chinese)[9] 罗军辉,姬红兵,刘靳. 一种基于空间滤波的红外小目标检测算法及其应用[J]. 红外与毫米波学报,2007,26(3):209-212. LUO J H, JI H B, LIU J. Algorithm of IR small targets detection based on spatial filter and its application [J]. Infrared Millin.Waves, 2007,26(3):209-212. (in Chinese)[10] 高陈强,田金文,王鹏,等. 复杂天空背景下基于GST的红外斑点小目标检测[J]. 华中科技大学学报(自然科学版),2009,37(7):10-13. GAO C Q, TIAN J W, WANG P. Detection of infrared spot small targets against complex sky background by using GST[J]. J. Huazhong Univ. of Sci. & Tech. (Natural Science Edition), 2009,37(7):10-13. (in Chinese)[11] 李波,姚春莲,李炜,等. 利用相邻帧和背景信息的运动对象检测[J]. 电子学报,2008(11):2154-2159. LI B, YAO CH L,LI W,et al.. A novel motion object detection algorithm using adjacent frame and background frame[J]. Acta Electronica Sinica, 2008(11):2154-2159. (in Chinese)

浏览量

373

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于目标增强与蝴蝶优化的红外与可见光图像融合

潜在低秩表示下的双判别器生成对抗网络的图像融合

基于弱监督学习的多标签红外图像分类算法

采用多尺度特征融合SSD的遥感图像小目标检测

基于改进多尺度分形特征的红外图像弱小目标检测