[1]许庆晗,金立左,费树岷.采用监督特征学习的红外小目标检测[J].东南大学学报(自然科学版),2011,41(5):1008-1012.[doi:10.3969/j.issn.1001-0505.2011.05.022]
 Xu Qinghan,Jin Lizuo,Fei Shumin.Small infrared target detection via supervised feature learning[J].Journal of Southeast University (Natural Science Edition),2011,41(5):1008-1012.[doi:10.3969/j.issn.1001-0505.2011.05.022]
点击复制

采用监督特征学习的红外小目标检测()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第5期
页码:
1008-1012
栏目:
计算机科学与工程
出版日期:
2011-09-20

文章信息/Info

Title:
Small infrared target detection via supervised feature learning
作者:
许庆晗金立左费树岷
(东南大学自动化学院,南京 210096)
Author(s):
Xu QinghanJin LizuoFei Shumin
(School of Automation, Southeast University, Nanjing 210096, China)
关键词:
小目标检测灰度分布特征相关向量机
Keywords:
small target detection feature of gray intensity distribution relevance vector machine
分类号:
TP391.41
DOI:
10.3969/j.issn.1001-0505.2011.05.022
摘要:
为了改善大尺寸图像下红外小目标检测的检测率与速度,提出一种采用监督特征学习的检测算法.通过分析小目标邻域图像的分布特点,定义一种基于灰度分布的统计特征,用以描述目标与非目标的邻域的灰度分布差异.以局部灰度极大值区域为训练样本,通过有监督学习提取对目标区分能力最强的特征.随后,在特征空间设计级联结构的多分类器,采用逻辑斯蒂回归和相关向量机分类器,通过“目标-非目标”分类,实现对目标的检测.实验结果表明在相同虚警率下,检测率较局部滤波法有一定提升,且检测速度大幅提高,满足了大尺寸图像下的实时性要求.
Abstract:
A supervised feature learning method is proposed for improving the detection probability and detection speed of small infrared target detection. Through analyzing the traits of small targets’ neighborhood image, a statistical feature based on gray intensity distribution is defined for describing the difference between the targets and nontargets’ neighborhood. Intensity extrema on global images are considered as training samples, and then a feature with the highest discriminability is extracted by supervised learning. Subsequently, a multi-stage classifier is designed in the feature space, which adopts logistic regression and relevance vector machine algorithms to detect targets via “target-nontarget” classification. Experimental results indicate that for large scale images and with the same false alarm rate, the proposed method is of higher probability of detection and much faster detection speed than local filtering methods.

参考文献/References:

[1] Tomasz A,Marcin K,Popiela T J,et al.Detection of clustered microcalcifications in small field digital mammography [J].Computer Methods and Programs in Biomedicine,2006,81(1):56-65.
[2] Bai X,Zhou F.Analysis of new top-hat transformation and the application for infrared dim small target detection [J].Pattern Recognition,2010,43(6):2145-2156.
[3] 杨磊.复杂背景条件下的红外小目标检测与跟踪算法研究 [D].上海:上海交通大学图像处理与模式识别研究所,2006.
[4] 刘靳,姬红兵.基于非平稳背景下的红外小目标检测 [J].电子与信息学报,2010,32(6):1295-1300.
  Liu Jin,Ji Hongbing.IR small targets detection based on non-homogeneous background[J].Journal of Electronics and Information Technology,2010,32(6):1295-1300.(in Chinese)
[5] 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.(in Chinese)
[6] Yang Q,Tan K,Ahuja N.Real-time O(1) bilateral filtering [C]//Proc of the Computer Vision and Pattern Recognition.Miami,USA,2009:557-564.
[7] 王鑫,唐振民.基于特征融合的粒子滤波在红外小目标跟踪中的应用 [J].中国图像图形学报,2010,15(1):91-97.
  Wang Xin,Tang Zhenmin.Application of particle filter based on feature fusion in small IR target tracking[J].Journal of Image and Graphics,2010,15(1):91-97.(in Chinese)
[8] Tang Z,Wang X.An efficient algorithm for infrared small target detection [C]//Proc of the 2nd International Conference on Information and Computing Science.Manchester,UK,2009:51-54.
[9] 杨磊,杨杰,凌建国,等.一种红外大视场环境下的多小目标实时检测方法 [J].红外与毫米波学报,2006,25(5):377-381.
  Yang Lei,Yang Jie,Ling Jianguo,et al.Real-time method for detecting multi-small targets in infrared large sight field[J].Journal of Infrared and Millimeter Waves,2006,25(5):377-381.(in Chinese)
[10] Viola P,Jones M.Rapid object detection using a boosted cascade of simple features [C]//Proc of the Computer Vision and Pattern Recognition.Kauai,HI,USA,2001:1511-1518.
[11] Friedman J,Hastie T,Tibshirani R.The elements of statistical learning [M].New York:Springer,2008:119-121.
[12] Tipping M E.Sparse Bayesian learning and the relevance vector machine [J].Journal of Machine Learning Research,2001,1:211-244.
[13] 张蕴奇.红外预警系统中的图像显示与目标检测方法研究 [D].西安:西安电子科技大学电子工程学院,2006.
[14] Hamdulla A,Lian X.High-resolution Bayes detection of dim moving point target in IR image sequence using probabilistic data association filter [C]//Proc of the Computer Science and Software Engineering.Wuhan,China,2008:365-368.

备注/Memo

备注/Memo:
作者简介:许庆晗(1982—),男,博士生;金立左(联系人),男,博士,副教授,jinlizuo@gmail.com.
基金项目:航空科学基金资助项目(20080169003).
引文格式: 许庆晗,金立左,费树岷.采用监督特征学习的红外小目标检测[J].东南大学学报:自然科学版,2011,41(5):1008-1012.[doi:10.3969/j.issn.1001-0505.2011.05.022]
更新日期/Last Update: 2011-09-20