采用核Rayleigh商二次相关滤波器的星图自适应杂波抑制

上海交通大学学报（自然版） ›› 2013, Vol. 47 ›› Issue (12): 1828-1835.

• 自动化技术、计算机技术 • 上一篇下一篇

采用核Rayleigh商二次相关滤波器的星图自适应杂波抑制

郭敬明1,2，何昕1，杨杰3，魏仲慧1

(1. 中国科学院长春光学精密机械与物理研究所，长春 130033；2. 中国科学院大学，北京 100039；3. 上海交通大学图像处理与模式识别研究所，上海 200240)

收稿日期:2013-02-22 出版日期:2013-12-28 发布日期:2013-12-28
基金资助:
国家高技术研究发展计划(863)资助项目(2006AA703405F)

Star Image Adaptive Clutter Suppression Using Kernel Rayleigh Quotient Quadratic Correlation Filter

GUO Jingming1,2,HE Xin1,YANG Jie3,WEI Zhonghui1

(1.Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Science, Changchun 130033, China; 2.University of Chinese Academy of Science, Beijing 100039, China;3. Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200240, China)

Received:2013-02-22 Online:2013-12-28 Published:2013-12-28

摘要/Abstract

摘要：

为了实现星图中弱小星点目标的检测，提出了一种基于核Rayleigh二次相关滤波器（KRQQCF）的星图自适应杂波抑制方法.采用星图模拟方法随机产生视轴指向，根据二维高斯模型产生训练样本，提取改进的加速鲁棒特征(SURF)，通过训练学习构建KRQQCF.为了快速检测目标，对待测图像首先用频域残差法检测星图中星点可能存在的显著性区域，然后提取该显著区域改进的5维SURF特征.最后，通过KRQQCF识别目标，有效抑制杂波及噪声，提高星图的信噪比.实验结果表明，该算法快速、有效、可靠.

关键词: 星图模拟, 加速鲁棒特征, 核Rayleigh商二次相关滤波器, 显著性

Abstract:

In order to detect small star point targets in star images, an adaptive clutter suppression algorithm based on kernel Rayleigh quotient quadratic correlation filter was proposed. The star image simulation method was adopted to generate optical axis point randomly, produce training samples according to the twodimensional Gaussian model, extract improved speed-up robust features(SURF), and learn to build kernel Rayleigh quotient quadratic correlation filter(KRQQCF). In order to detect the target quickly, for the image to be detected, the spectral residual method was used to detect salient regions probably containing targets. Then the improved 5-dimension SURF feature of the salient regions was extracted. Finally, the target was recognized using KRQQCF, and the clutter and noise were suppressed effectively which improved the SNR. Experimental results indicate that the proposed algorithm is fast, effective and robust.

Key words: star image simulation, speed-up robust feature (SURF), kernel Rayleigh quotient quadratic correlation filter (KRQQCF), saliency

中图分类号:

TP 391

郭敬明1,2，何昕1，杨杰3，魏仲慧1. 采用核Rayleigh商二次相关滤波器的星图自适应杂波抑制[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1828-1835.

GUO Jingming1,2,HE Xin1,YANG Jie3,WEI Zhonghui1. Star Image Adaptive Clutter Suppression Using Kernel Rayleigh Quotient Quadratic Correlation Filter[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1828-1835.

参考文献

［1李德良,阮景.一种适用于星敏感器的星点提取方法［J］.激光与红外,2009,39(12):13481350.

LI Deliang, RUAN Jin. Method adapting to the star sensor’s star extraction［J］.

Laser and Infrared,2009,39(12):13481350.

［2］原玉磊,郑勇.一种大视场星图星点提取的阈值方法［J］.海洋测绘,2011,31(5):4143.

YUAN Yulei, ZHENG Yong. A threshold segmentation method of star extraction in large field star image［J］. Hydrographic Surveying and Charting,2011,31(5):4143.

［3］曾明,李建勋.基于自适应形态学TopHat滤波器的红外弱小目标检测方法［J］.

上海交通大学学报,2006,40(1):9093.

ZENG Ming, LI Jianxun. The small target detection in infrared image based on adaptive morphological TopHat filter［J］.Journal of Shanghai Jiaotong University, 2006,40(1):9093.

［4］Mahalanobis A, Muise R R, Stanfill S R, et al. Design and application of quadratic correlation filters for target detection［J］.IEEE Transactions on Aerospace and Electronics Systems,2004,40(3):837850.

［5］Mahalanobis A, Muise R R, Stanfill S R.Quadratic correlation filter design methodology for target detection and surveillance applications［J］.Applied Optics,

2004,43(27):51985205.

［6］刘瑞明，刘尔琦，杨杰，等.核FukunagaKoontz变换检测红外小目标［J］.

红外与毫米波学报, 2008,27(1):4751.

LIU Ruiming, LIU Erqi, YANG Jie,et al. Infrared small target detection with kernel FukunagaKoontz transform［J］.Journal of Infrared and Millimeter Waves,2008,27(1):4751.

［7］吴燕茹,程咏梅,赵永强,等.基于核Rayleigh商二次相关滤波器的红外目标检测［J］.红外与毫米波学报,2011,30(2):142148.

WU Yanru, CHENG Yongmei, ZHAO Yongqiang, et al. Infrared target detection using kernel Rayleigh quotient quadratic correlation filter［J］. Journal of Infrared and Millimeter Waves,2011,30(2):142148.

［8］Lowe David G. Distinctive image features from scaleinvariant keypoints［J］. International Journal of Computer Vision,2004, 60(2): 91110.

［9］Herbert B, Andreas E, Tinne T, et al.Speed up robust features ［J］. Computer Vision and Image Understanding, 2008, 110(3):346359.

［10］Javier R, Patricio L, Pablo Z. Applying SIFT descriptors to stellar image matching［C］∥CIARP. Havana: Springer, 2008:618625.

［11］Luo J, Oubong G. A comparison of SIFT, PCASIFT, and SURF［J］. International Journal of Image Processing,2009,3(4):143152.

［12］Hou Xiaodi, Zhang Liqing. Saliency detection: A spectral residual approach［C］∥IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis. MN:IEEE Press, 2007: 18.

［13］郭敬明,魏仲慧,何昕,等.CCD星图模拟器的设计及验证［J］.中国光学与应用光学,2010,3 (5):486493.

GUO Jingming, WEI Zhonghui, HE Xin,et al.Design of CCD star map simulator and its validation［J］. Chinese Journal of Optics and Applied Optics,2010,3 (5):486493.

［14］Yang Jian, Frangi A F, Yang JingYu, et al. KPCA plus LDA: A complete kernel Fisher discriminant framework for feature extraction and recognition［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(2):230244.

[1]	荣雪宁，卢浩，王明洋，文祝，戎晓力，王振. 基于刀盘扭转能量的土压平衡盾构刀具磨损分析[J]. 上海交通大学学报, 2019, 53(8): 965-970.
[2]	陈东岳，陈宗文. 基于特征显著性的均值漂移鲁棒目标跟踪[J]. 上海交通大学学报（自然版）, 2013, 47(11): 1807-1812.
[3]	陈硕, 于晓升, 吴成东, 陈东岳. 用于场景分类的显著建筑物区域检测[J]. 上海交通大学学报（自然版）, 2011, 45(08): 1130-1135.
[4]	李武跃，李志强，方涛，霍宏，葛卫丽. 基于颜色信息相位谱的显著性检测[J]. 上海交通大学学报（自然版）, 2008, 42(10): 1613-1617.

采用核Rayleigh商二次相关滤波器的星图自适应杂波抑制

Star Image Adaptive Clutter Suppression Using Kernel Rayleigh Quotient Quadratic Correlation Filter

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价