基于FLS-SVM背景预测的红外弱小目标检测

吴一全; 尹丹艳

doi:doi:10.3788/aos20103010.2806

光学学报, 2010, 30 (10): 2806, 网络出版: 2012-10-24

基于FLS-SVM背景预测的红外弱小目标检测

Detection of Small Target in Infrared Image Based on Background Predication by FLS-SVM

论文大纲

吴一全 ^1,2,*尹丹艳 ¹

作者单位

¹ 南京航空航天大学信息科学与技术学院，江苏南京 210016

² 南京大学计算机软件新技术国家重点实验室，江苏南京 210093

摘要

提出了一种基于模糊最小二乘支持向量机(FLS-SVM)进行背景预测、利用模糊Tsallis-Havrda-Charvat熵实现阈值分割的红外弱小目标检测方法。首先采用FLS-SVM对训练样本进行学习得到回归函数，并以此预测红外图像中的背景；然后将原始图像与预测图像相减得到残差图像，并提出基于模糊Tsallis-Havrda-Charvat熵的阈值选取算法分割残差图像，将小目标和噪声从残差背景中分割出来；最后利用目标灰度的平稳性和运动轨迹的连续性进一步检测出真实的小目标。给出了实验结果及分析，并与基于最小二乘支持向量机(LS-SVM)以及基于最小二乘的背景预测方法的检测结果进行了比较。结果表明，该方法具有更高的检测概率和信噪比增益，优于上述基于背景预测的红外小目标检测方法。

Abstract

A detection method of small target in infrared image is proposed, which is based on the background predication by fuzzy least squares support vector machine (FLS-SVM) and threshold segmentation by fuzzy Tsallis-Havrda-Charvat entropy. Firstly, the fitting function is obtained from the training samples by using FLS-SVM and the background in infrared image is predicted. Then, the predicted image subtracted from the source image gives the residual-error image. The residual-error image is segmented by the proposed threshold selection method based on fuzzy Tsallis-Havrda-Charvat entropy so as to separate small target and noise from the residual background. Finally, the true small target is further detected based on the stability of the target gray and the consistency of target trajectory. The experimental results are given and analyzed. They are compared with the detection results of the background predication methods based on LS-SVM or least squares. The results show that the proposed method has higher detection probability and the gain of signal-to-noise ratio (GSNR) and it is superior to the above-mentioned methods.

参考文献

[1] 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 Duyan. Characteristic-selecting filtering in infrared small target detection［J］. Acta Optica Sinica, 2009, 29(9): 2408～2412

[2] 李欣, 赵亦工, 陈冰. 基于分类的红外云层背景弱小目标检测方法［J］. 光学学报, 2009, 29(11): 3036～3042

Li Xin, Zhao Yigong, Chen Bing. A new approach of small and dim target detection in cloud cluster infrared image based on classification［J］. Acta Optica Sinica, 2009,29(11): 3036～3042

[3] Bai Xiangzhi, Zhou Fugen. Analysis of new top-hat transformation and the application for infrared dim small target detection［J］. Pattern Recogn., 2010, 43(6): 2145～2156

[4] Li Hong, Wei Yantao, Li Luoqing et al.. Infrared moving target detection and tracking based on tensor locality preserving projection［J］.Infrared Phys. Technol., 2010, 53(2): 77～83

[5] Zhang Tianxu, Li Meng, Zuo Zhengrong et al.. Moving dim point target detection with three-dimensional wide-to-exact search directional filtering［J］. Pattern Recogn. Lett., 2007, 28(2): 246～253

[6] 朱金标, 李建勋. 匹配滤波器优化设计及在红外弱小点目标检测中的应用［J］. 光学学报, 2009, 29(8): 2128～2133

Zhu Jinbiao, Li Jianxun. Novel matching filter design and its application on dim point target detection in infrared image［J］. Acta Optica Sinica, 2009, 29(8): 2128～2133

[7] 凌建国, 刘尔琦, 杨杰等. 基于H∞滤波器的红外小目标运动预测和跟踪方法［J］. 红外与毫米波学报, 2005, 24(5): 366～369

Ling Jianguo, Liu Erqi, Yang Jie et al.. Approach of infrared small target motion prediction and tracking based on H∞ filter［J］. J. Infrared Millim. W., 2005, 24(5): 366～369

[8] 胡谋法, 沈燕, 陈曾平. M滤波的自适应背景抑制算法［J］. 光电子·激光, 2007, 18(1): 104～107

Hu Moufa, Shen Yan, Chen Zengping. New adaptive background suppression algorithm via M-filter［J］. J. Optoelectronics·Laser, 2007, 18(1): 104～107

[9] Zhang Biyin, Zhang Tianxu, Zhang Kun et al.. Adaptive rectification filter for detecting small IR targets［J］ . IEEE T. Aero. Elec. Sys., 2007, 22(8): 20～26

[10] 李凡, 刘上乾, 洪鸣等. 基于背景预测的红外弱小目标检测新算法［J］. 西安电子科技大学学报,2009,36(6): 1075～1078

Li Fan, Liu Shangqian, Hong Ming et al.. Dim infrared targets detection based on background prediction［J］. J. Xidian University, 2009, 36(6): 1075～1078

[11] 吴一全, 吴文怡. 基于变邻域变步长LMS背景预测检测红外小目标［J］. 宇航学报, 2009, 30(2): 735～739

Wu Yiquan, Wu Wenyi. Infrared small target detection based on adaptive prediction of background by variable neighborhood and step-size LMS algorithm［J］. J. Astronautics, 2009, 30(2): 735～739

[12] 胡谋法, 陈曾平. 基于Zernike-Facet模型和总体最小二乘的弱小目标检测［J］. 电子与信息学报, 2008, 30(1): 194～197

Hu Moufa, Chen Zengping. New small target detection algorithm via zernike-facet model and total least squares［J］. J. Electron. & Info. Technol., 2008, 30(1): 194～197

[13] 吴一全, 吴文怡, 罗子娟. 基于最小一乘和混沌遗传算法检测红外小目标［J］. 光子学报, 2009, 38(3): 736～740

Wu Yiquan ,Wu Wenyi ,Luo Zijuan. A method of small target detection in infrared image sequences based on the least absolute deviation and chaos-genetic algorithms［J］. Acta Photonica Sinica 2009, 38(3): 736～740

[14] H. Leung, N. Dubash, N. Xie. Detection of small objects in clutter using a GA-RBF neural network［J］. IEEE T. Aero. Elec. Sys., 2002, 38(1): 98～118

[15] 张焱, 沈振康, 王平. 基于RBF神经网络的背景估计及红外小目标检测［J］. 国防科技大学学报,2004, 26(5): 39～45

Zhang Yan, Shen Zhenkang, Wang Ping. Background estimation and the infrared small target detection based on RBF neural network［J］. J. National University of Defense Technology, 2004, 26(5): 39～45

[16] David Casasent, Yu-Chiang Wang. A hierarchical classifier using new support vector machines for automatic target recognition［J］. Neural Networks, 2005, 18: 541～548

[17] P. Wang, J. W. Tian, Ch.Q. Gao. Infrared small target detection using directional highpass filters based on LS-SVM［J］. Electron. Lett., 2009, 45(3): 156～158

[18] C. J. C. Burges. A tutorial on support vector machines for pattern recognition［J］. Data Min Knowl. Disc., 1998, 2:121～167

[19] 吴一全, 潘喆, 吴文怡. 二维直方图斜分Tsallis-Havrda-Charvát熵图像阈值分割［J］. 光电工程, 2008, 35(7): 53～58

Wu Yiquan, Pan Zhe, Wu Wenyi. Tsallis-Havrda-Charvát entropy image thresholding based on two-dimensional histogram oblique segmentation［J］. Opto-Electronic Engineering, 2008, 35(7): 53～58

吴一全, 尹丹艳. 基于FLS-SVM背景预测的红外弱小目标检测[J]. 光学学报, 2010, 30(10): 2806. Wu Yiquan, Yin Danyan. Detection of Small Target in Infrared Image Based on Background Predication by FLS-SVM[J]. Acta Optica Sinica, 2010, 30(10): 2806.

基于FLS-SVM背景预测的红外弱小目标检测

关于本站 Cookie 的使用提示

全站搜索

基于FLS-SVM背景预测的红外弱小目标检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索