各向异性SUSAN滤波红外弱小目标检测

景亮; 彭真明; 何艳敏; 蒲恬

doi:doi:10.3788/hplpb20132509.2208

强激光与粒子束, 2013, 25 (9): 2208, 网络出版: 2013-08-28

各向异性SUSAN滤波红外弱小目标检测

Infrared dim target detection based on anisotropic SUSAN filtering

论文大纲

景亮 ^*彭真明何艳敏蒲恬

作者单位

电子科技大学光电信息学院, 成都 610054

SUSAN滤波器各向异性滤波背景建模红外图像弱小目标检测 SUSAN filter anisotropic filtering background modeling infrared image dim target detection

摘要

为了解决SUSAN滤波算子不能自适应调整滤波系数的问题，采用Geusebroek提出的各向异性高斯滤波器替代SUSAN滤波算子中的高斯滤波部分。由局部图像的方差和像素的邻域平滑度决定长短轴的方差，由该点的梯度方向决定滤波器的长轴方向，由局部图像的灰度值与均值差的一阶范数确定SUSAN滤波器的阈值，从而构造出各向异性SUSAN滤波器。将其用于红外弱小目标检测中，实验结果表明：各向异性SUSAN滤波器能够很好地保留图像中的边缘信息，使残差图像中弱小目标的信噪比增益和信杂比增益极大地提高，目标大小得到较好的保留，虚警率下降。

Abstract

The SUSAN filtering operator can not selfadaptively modulate filter coefficients due to the use of an axisymmetric Gaussian filter. In order to solve this problem, this article presents an anisotropic SUSAN filter using an anisotropic Gaussian filter instead of a Gaussian filter in the SUSAN filtering operator. The variances of long axis and short axis are determined by the variance and the pixel neighborhood smoothness of the partial image. The long axis direction is determined by the gradient direction of the point. The SUSAN filter threshold is determined by the first order norm of the difference of the gray value and the mean value. For the infrared dim target detection, experimental results show that the anisotropic SUSAN filter could preserve the image edge information, the signaltonoise ratio gain and signaltoclutter ratio gain greatly improved in the residual image, the size of the target got a better retention, and the false alarm decreased.

参考文献

[1] Geusebroek J M, Smeulders A W M, Weijer J V D. Fast anisotropic Gauss filtering［J］. IEEE Trans on Image Processing, 2003, 12(8): 938-943.

[2] 严高师, 毕务忠. 基于区域奇异性滤波的小目标检测［J］. 光学技术, 2007, 33(2): 163-166.(Yan Gaoshi, Bi Wuzhong. Detection algorithm of small target based on regional singularity filter. Optical Technique, 2007, 33(2): 163-166)

[3] 王怀野, 张科, 李言俊. 各向异性滤波在红外图像处理中的应用［J］. 红外与毫米波学报, 2005, 24(2): 109-113.(Wang Huaiye, Zhang Ke, Li Yanjun. Anisotropic Gaussian filtering for infrared image. J Infrared Millim Waves, 2005, 24(2): 109-113)

[4] Smith S M, Brady J M. SUSAN—A new approach to low level image processing［J］. International Journal of Computer Vision, 1997, 23(1):45-78.

[5] 许兵, 尹宏杰, 朱珺, 等. 基于SUSAN及其改进算法的InSAR干涉图滤波研究［J］. 大地测量与地球动力学, 2010, 30(4): 68-73.(Xu Bing, Yin Hongjie, Zhu Jun, et al. InSAR interferogram filtering based on SUSAN and its improved algorithm. Journal of Geodesy and Geodynamics, 2010, 30(4): 68-73)

[6] Duan X H, Zheng G F, Chao H Y. An adaptive realtime descreening method based on SVM and improved SUSAN filter［C］//ICASSP. 2010: 1462-1465.

[7] Boccignone G, Chianese A, Picariello A. Small target detection using wavelets［C］//IEEE International Conference on Pattern Recognition. 1998, 2: 1776-1778.

[8] 汪大宝, 刘上乾, 张峰. 一种新的红外复杂背景自适应抑制算法［J］. 西安电子科技大学学报：自然科学版, 2010, 37(5): 927-933.(Wang Dabao, Liu Shangqian, Zhang Feng. New adaptive infrared strong cluttered background suppression algorithm. Journal of Xidian University: Nature Science Edition, 2010, 37(5): 927-933)

[9] 张路, 张志勇, 肖山竹, 等. 基于多向背景预测的红外弱小目标检测［J］. 信号处理, 2010, 26(11): 1646-1651.(Zhang Lu, Zhang Zhiyong, Xiao Shanzhu, et a1. Detection of dim infrared targets by multidirection prediction of background. Signal Processing, 2010, 26(11): 1646-1651)

[10] 彭真明, 张启衡, 王敬儒, 等. 一种弱小目标的自适应搜索方法［J］. 光电工程, 2003, 30(4): 15-19.(Peng Zhenming, Zhang Qiheng, Wang Jingru, et a1. A searching method for faint targets. OptoElectronic Engineering, 2003, 30(4): 15-19)

[11] 彭真明, 蒋彪, 肖峻. 基于脉冲耦合神经网络的空中扩展目标检测［J］. 强激光与粒子束, 2007, 19(12): 2011-2016.(Peng Zhenming, Jiang Biao, Xiao Jun. Aerial extended target detection based on unitlinking pulse coupled neural networks. High Power Laser and Particle Beams, 2007, 19(12): 2011-2016)

[12] 赵佳佳, 唐峥远, 杨杰, 等. 基于图像稀疏表示的红外小目标检测算法［J］. 红外与毫米波学报, 2011, 30(2): 156-162.(Zhao Jiajia, Tang Zhengyuan, Yang Jie, et a1. Infrared small target detection based on image sparse representation. J Infrared Millim Waves, 2011, 30(2): 156-162)

[13] 陈卉, 欧阳楷. 用于图像增强的侧抑制网络模型的仿真比较［J］. 系统仿真学报, 2003, 15(1): 100-103.(Chen Hui, Ouyang Kai. Simulation comparison of lateral inhibition models in image enhancement. Journal of System Simulation, 2003, 15(1): 100-103)

[14] 史漫丽, 彭真明, 张启衡, 等. 基于自适应侧抑制网络的红外弱小目标检测［J］. 强激光与粒子束, 2011, 23(4): 906-910.(Shi Manli, Peng Zhenmin, Zhang Qihen, et a1. Dim infrared target detection based on adaptive lateral inhibition network. High Power Laser and Particle Beams, 2011, 23(4): 906-910)

[15] 张从力, 王述勇, 王莲. 一种具有保留边缘信息的改进SUSAN去噪方法［J］.研究与开发, 2007, 26(10): 33-35.(Zhang Congli, Wang Shuyong, Wang Lian. Improved SUSAN filter with edge information reserved. Research and Development, 2007, 26(10): 33-35)

景亮, 彭真明, 何艳敏, 蒲恬. 各向异性SUSAN滤波红外弱小目标检测[J]. 强激光与粒子束, 2013, 25(9): 2208. Jing Liang, Peng Zhenming, He Yanmin, Pu Tian. Infrared dim target detection based on anisotropic SUSAN filtering[J]. High Power Laser and Particle Beams, 2013, 25(9): 2208.

各向异性SUSAN滤波红外弱小目标检测

关于本站 Cookie 的使用提示

全站搜索

各向异性SUSAN滤波红外弱小目标检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索