基于非平稳背景下的红外小目标检测

刘靳; 姬红兵

doi:10.3724/SP.J.1146.2009.01083

基于非平稳背景下的红外小目标检测

doi: 10.3724/SP.J.1146.2009.01083

刘靳,
姬红兵

计量
- 文章访问数: 3202
- HTML全文浏览量: 83
- PDF下载量: 909
- 被引次数: 0
出版历程
- 收稿日期: 2009-08-13
- 修回日期: 2010-01-25
- 刊出日期: 2010-06-19

IR Small Targets Detection Based on Non-homogeneous Background

摘要

摘要: 针对非平稳复杂背景下单帧图像的红外小目标检测概率较低的问题，该文提出了一种基于当前残差的改进M估计的红外背景预测和抑制算法。该算法利用M估计的基本模型预测背景，将目标像素和观测噪声视为背景估计的混合干扰，提出与背景图像残差相关的校正函数c()自适应地调整估计增益，从而减小异常样本对背景估计的影响，提高了估计的准确性。同时引入遗忘因子使算法能够适应于非均匀复杂背景的估计，提高了算法的鲁棒性。多组红外图像实验表明：所提算法不仅能够在非平稳背景下有效地估计背景，还能在滤除背景的同时最大程度地保留目标像素的信息，提高了目标的检测概率。
- 小目标检测; 非平稳背景估计; M估计模型; 校正函数; 遗忘因子
Abstract: For lower detection probability problem of small IR targets in a complex non-homogeneous background, an improved M-estimation filtering algorithm based on residual is proposed to suppress background clutters. The algorithm introduces the basic model of M-estimation to predict background, and target pixels and observed noise are considered as the mixed interference of background estimation. It puts forward the correction function c() related to residual to adaptively adjust gain to reduce the abnormal samples influence of background estimation and increases the accuracy of estimation. Meanwhile, the proposed algorithm uses the forget factor to entreat the non-homogeneous background prediction and the robustness is improved. Experimental results on IR images illustrate that the proposed algorithm can not only predict background effectively in non-homogeneous background but preserve targets information to maximum extent. As a result, the proposed algorithm has higher detection probability.

HTML全文

参考文献(1)

Wang Jing, Bao Shang-qi, and Ralph J F, et al.. Detection of small objects in multi-layered infrared images [C]. Signal and Data Processing of Small Targets, 2008. Proceedings of the SPIE, 2008, 6969: 696905-696905-8.[2]Wemett B D. Automatic target detection using vector quantization error [C]. Automatic Target Recognition XVIII. Proceedings of the SPIE, 2008, 6967: 696712-696712-10.[3]宗思光, 王江安. 基于形态学图像融合的目标检测方法 [J]. 光电子激光, 2004, 15(2): 208-211.Zong Si-guang and Wang Jiang-an. Infrared image targets detection based on multi-scale mathematical morphology fusion [J].Journal of OptoelectronicsLaser.2004, 15(2):208-211[4]陈远, 王凌, 冯华君等. 高散射介质后向扩散散射实验的图像预处理 [J]. 光电子激光, 2005, 16(11): 1373-1377.Chen Yuan, Wang Ling, and Feng Hua-jun, et al.. Image pre-processing for diffuse backscattering of polarized light from highly scattering media [J].Journal of OptoelectronicsLaser.2005, 16(11):1373-1377[5]Manolakis D G, Ingle V K, and Kogon S M. Statistical and Adaptive Signal Processing [M]. Boston: McGraw-Hill Science/Engineering/Math, 1999, Chapter 8.[6]Wang P, Tian J W, and Gao C Q. Infrared small target detection using directional high pass filters based on LS-SVM [J].Electronics Letters.2009, 45(3):156-158[7]Tang Zhen-min and Wang Xin. An efficient algorithm for infrared small target detection [C][J].Second International Conference on Information and Computing Science ICIC0.2009, 2:51-54[8]曹瑛, 李志永, 卢晓鹏等. 基于自适应领域双边滤波的点目标检测预处理算法[J].电子与信息学报.2008, 30(8):1909-1912浏览Cao Ying, Li Zhi-yong, and Lu Xiao-peng, et al.. A preprocessing algorithm of point target detection based on temporal-spatial bilateral filter using adaptive neighborhoods [J].Journal of Electronics Information Technology.2008, 30(8):1909-1912[9]Huber P J and Ronchetti E M. Robust Statistics (2nd Ed.) [M]. New York: Wiley, 2009, Chapter 3.[10]Haykin S. Adaptive Filter Theory (4th Ed.) [M]. US, Prentice Hall, 2001, Chapter 8.[11]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 Jun-hui, Ji Hong-bing, and Liu Jin. Algorithm of IR small targets detection based on spatial filter and its application [J]. Journal of Infrared and Millimeter-wave, 2007, 26(3): 209-212.[12]Braga-Neto U, Choudhary M, and Goutsias J. Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators [J].Journal of Electronic Imaging.2004, 13(4):802-813

施引文献

资源附件(0)

访问统计