采用降维技术的红外目标检测与识别

李一芒; 何昕; 魏仲慧; 郭敬明

doi:10.3788/OPE.20132105.1297

您当前的位置：

首页 >

文章列表页 >

采用降维技术的红外目标检测与识别

信息科学 | 更新时间：2020-08-12

- 采用降维技术的红外目标检测与识别
- Infrared targets detection and recognition using dimension reduction technology
- 光学精密工程 2013年21卷第5期页码：1297-1303
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所,吉林长春,130033
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132105.1297
  中图分类号： TN216;TP391.4
- 收稿日期：2012-03-05，
  
  修回日期：2012-04-15，
  
  网络出版日期：2013-05-24，
  
  纸质出版日期：2013-05-15
- 稿件说明：
移动端阅览
李一芒何昕魏仲慧郭敬明. 采用降维技术的红外目标检测与识别[J]. 光学精密工程, 2013,21(5): 1297-1303

LI Yi-Mang WEI Zhong-hui GUO Jing-Ming. Infrared targets detection and recognition using dimension reduction technology[J]. Editorial Office of Optics and Precision Engineering, 2013,21(5): 1297-1303
李一芒何昕魏仲慧郭敬明. 采用降维技术的红外目标检测与识别[J]. 光学精密工程, 2013,21(5): 1297-1303 DOI： 10.3788/OPE.20132105.1297.

LI Yi-Mang WEI Zhong-hui GUO Jing-Ming. Infrared targets detection and recognition using dimension reduction technology[J]. Editorial Office of Optics and Precision Engineering, 2013,21(5): 1297-1303 DOI： 10.3788/OPE.20132105.1297.

摘要

提出了一种用于扫描型红外预警系统的目标检测与识别算法来实现对空中威胁的预警

该算法在对目标进行检测和识别的过程中分别运用了降维技术。首先对拉普拉斯-高斯（Laplacian of Gaussian

LOG)算子降维，改变经典LOG算子各向同性的特点，从而减少了信息的丢失；然后通过设置相关参数设计8邻域方位滤波器对图像不同方向进行尺度优化的滤波以完成目标增强与背景抑制；最后对滤波结果进行目标提取，通过支持向量机算法对目标进行识别。为使识别过程更加简捷而不失准确性，在识别前采用基于协方差算子的充分降维方法对样本特征和目标特征进行降维，从而在简化经典滤波算法与目标识别算法的同时提升了算法效率。实验结果表明，与经典高维算法相比，本文提出的算法在对红外目标进行检测识别时能够获得更好的效果，应用于工程时能实现低于7%的虚警率和低于5%的漏警率，且算法能够满足系统实时性要求。

Abstract

An algorithm combined target detection and target recognition for a scanning infrared early-warning system was proposed to realize early-warning of air threats. First

the dimension of Laplacian of Gaussian （LOG） operator was reduced to change the isotropic characteristics of classical LOG operator and to reduce its information losses. Then

an eight-neighborhood local filter was proposed to enhance targets and suppress backgrounds by setting relevant parameters. Finally

the targets were extracted from filted results and were recognized by the Support Vector Machine(SVM) algorithm. In order to simplify the recognition procedure within preciseness

the Sufficient Dimension Reduction (SDR) based on the covariance operator was used to reduce the feature dimensions of samples and targets before recognition so that to simplify the classical filter and recognition algorithm while to improve the algorithm efficiency. Experimental results indicate that the proposed method gets better results than the high-dimensional algorithm and it can satisfy the system requirements of real-time performance. The false-warning rate and the miss-warning rate are lower than 7% and 5%

respectively.

关键词

Keywords

references

靳永亮,王延杰,刘艳滢，等.红外弱小目标的分割预检测[J]. 光学精密工程，2012，20(1): 171-178.JIN Y L, WANG Y J, LIU Y Y, et al.. Pre-detection method for small infrared target[J]. Opt. Precision Eng., 2012, 20(1): 171-178. (in Chinese)[2]高晶,孙继银,刘婧，等.基于区域模糊阈值的前视红外目标识别[J]. 光学精密工程，2011，19(12): 3056-3063.GAO J, SUN J, LIU J, et al.. FLIR target recognition based on local fuzzy threshold[J]. Opt. Precision Eng., 2011, 19(12): 3056-3063. (in Chinese)[3]李一芒，何昕，魏仲慧.红外预警实时图像处理系统设计与实现[J]. 液晶与显示，2013,28（1）：110-114.LI Y M, HE X, WEI Z H. Design and implement of real-time image processing system for IR warning system based on multi-passage [J]. Chinese Journal of Liquid Crystals and Displays, 2013,28（1）：110-114. (in Chinese)[4]穆治亚，魏仲慧，何昕，等.基于NIOS II的红外弱小目标检测算法实现[J]. 液晶与显示，2012,27（6）：814-819.MU Z Y, WEI Z H, HE X.Design of dim-small target detection on infrared image based on NIOS II[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27（6）：814-819. (in Chinese) [5]丘文涛,赵建,刘杰. 结合区域分割的SIFT图像匹配方法[J]. 液晶与显示,2012,27(6): 827-831.QIU W T，ZHAO J，LIU J. Image matching algorithm combining SIFT with region segmentation[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(6): 827-831. (in Chinese)[6]吴君钦,刘昊,罗勇. 静态背景下的运动目标检测算法[J]. 液晶与显示,2012,27(5): 682-686.WU J Q, LIU H, LUO Y. Algorithm of moving object dection in static background[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(5): 682-686. (in Chinese)[7]李英，李静宇，徐正平. 结合SURF与聚类分析方法实现运动目标的快速跟踪[J]. 液晶与显示，2011, 26（4）：544-550.LI Y，LI J Y，XU ZH P. Moving target fast tracking using SURF and cluster analysis method [J]. Chinese Journal of Liquid Crystals and Displays, 2011, 26（4）：544-550. (in Chinese)[8]GILLES A, ALEXIS B, LAURE B, et al.. Detection and tracking of threats in aerial infrared images by a minimal path approach[J]. IEEE Journal On Sophia, 2010：1658-1661.[9]ALEXANDER G. TARTAKOVSKY, JAMES B. Adaptive spatial-temporal filtering methods for clutter removal and target tracking[J]. IEEE Transactions on Aerospace And Electronic Systems,2008, 4(48):1522-1537.[10]郭志军,何昕,魏仲慧.推扫式实时图像目标识别处理系统的设计[J]. 光电工程，2011，38(1): 15-22.GUO Z J, HE X, WEI Z H. Design of recognition system based on the real-time scan-image processing [J]. Opto-Electronic Engineering,2011, 38(1): 15-22. (in Chinese)[11]於州.充分降维理论和方法的拓展研究\[D\]. 上海：华东师范大学，2010：1-9.YU Z. Extending the Scope of Sufficient Dimension Reduction Theory and Its Related Methods \[D\]. shanghai：East China Normal University.2010: 1-9. (in Chinese)[12]关斌.一种改进的自适应各向异性LOG算子[J]. 科学技术与工程，2010,37(3):210-212.GUAN B. Improved self-adaptable anisotropic laplacian of gaussian operator[J]. Science Technology and Engineering， 2010, 37(3): 210-212. (in Chinese)

浏览量

138

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于空时域融合处理检测超大视场红外目标

跨层注意力交互下的多特征交叉无人机图像检测

改进YOLOv7的服务机器人密集遮挡目标识别

适应大范围星场密度变化的恒星辨识与抑制

利用光谱解混合的目标检测