基于不变特征描述符实现星点匹配

翟优; 曾峦; 熊伟

doi:10.3788/OPE.20122011.2531

您当前的位置：

首页 >

文章列表页 >

基于不变特征描述符实现星点匹配

信息科学 | 更新时间：2020-08-12

- 基于不变特征描述符实现星点匹配
- Star matching based on invariant feature descriptor
- 光学精密工程 2012年20卷第11期页码：2531-2539
- 作者机构：
  
  中国人民解放军装备学院北京,101416
- 作者简介：
- 基金信息：
  
  省部级试验技术研究项目(No.2009SY4110005)()
- DOI：10.3788/OPE.20122011.2531
  中图分类号： TP391.4
- 收稿日期：2012-07-10，
  
  修回日期：2012-08-15，
  
  纸质出版日期：2012-11-10
- 稿件说明：
移动端阅览
翟优, 曾峦, 熊伟. 基于不变特征描述符实现星点匹配[J]. 光学精密工程, 2012,20(11): 2531-2539

ZHAI You, ZENG Luan, XIONG Wei. Star matching based on invariant feature descriptor[J]. Editorial Office of Optics and Precision Engineering, 2012,20(11): 2531-2539
翟优, 曾峦, 熊伟. 基于不变特征描述符实现星点匹配[J]. 光学精密工程, 2012,20(11): 2531-2539 DOI： 10.3788/OPE.20122011.2531.

ZHAI You, ZENG Luan, XIONG Wei. Star matching based on invariant feature descriptor[J]. Editorial Office of Optics and Precision Engineering, 2012,20(11): 2531-2539 DOI： 10.3788/OPE.20122011.2531.

摘要

为了能够在星图存在旋转角度情况下

自动快速地完成星图匹配

提出了一种基于不变特征描述符的旋转不变匹配方法

将加速鲁棒特征(SURF)描述符应用于星点特征的描述和匹配。首先

对星图进行图像分割

抑制非极大值

并检测星点;然后

为计算星点分布尺度因子

在半径为6

的圆形邻域内为每个星点计算主方向

之后将20

的邻域与主方向对准

并在该邻域内为每个星点计算SURF描述符。最后

基于透视投影模型的匹配策略

提纯星点

计算匹配星图之间的变换矩阵。实验结果显示

该方法能够鲁棒地提取星点

并在图像存在旋转、平移及部分视角变化的情况下完成星图匹配

仿真实验的匹配星点的误差均在1 pixel以下

实拍星图实验的匹配星点的误差均在1.5 pixel以下

表明为每个星点建立描述符

进行匹配识别的思路是可行的。

Abstract

To match automatically rotated stellar images

a rotation invariant matching method based on invariant feature descriptors was proposed

in which the Speeded Up Robust Features (SURF) was used to describe and match star features for the first time. First

a stellar image was segmented

and the non-maxima value was suppressed to extract star points in the stellar image. Then

a star distribution scale factor was calculated

the dominant orientation was obtained in a circle region with a radius of 6

and the 20

local region was rotated to the dominant orientation. In the local region

the SURF descriptor was calculated for each star. Finally

an automatic matching strategy based on the difference between dominant orientations was proposed. By this method

the threshold was calculated automatically and the transform matrix was given. Experimental results demonstrate that the proposed method can robustly detect star features and achieve a high precision stellar image matching between images with rotation

translation and perspective change. Obtained results show that correspondent star errors is below 1 pixel and 1.5 pixel for simulation and real image experiments

respectively. It indicates that the method to apply SURF descriptor to star matching and recognition is feasible.

关键词

Keywords

references

李真真,魏宏刚. 亮背景下形态学星点目标提取算法[J]. 光电工程, 2011, 38(12): 23-27. LI ZH ZH, WEI H G. The algorithm of star extraction based on mathematical morphology in the bright-background [J]. 2011, 38(12): 23-27.(in Chinese)[2] 王海涌,费峥红,王新龙. 基于高斯分布的星像点精确模拟及质心计算[J]. 光学精密工程, 2009,17(7): 1672-1677. WANG H Y, FEI ZH H, WANG X L. Precise simulation of star spots and centroid calculation based on Gaussian distribution [J]. Opt. Precision Eng., 2009, 17(7): 1672-1677. (in Chinese)[3] 刘太阳,王仕成,刘志国. 多步变权重复合的通用星点聚心[J]. 光学精密工程, 2011, 19(10) : 2494-2499. LIU T Y, WANG SH CH, LIU ZH G. Universal star centroiding with stepping variant weighting integration [J]. Opt. Precision Eng., 2011, 19(10): 2494-2499. (in Chinese)[4] 孙瑾秋,周军. 基于能量累加的空间目标星像质心定位[J]. 光学精密工程, 2011, 19(12): 3043-3048. SUN J Q, ZHOU J. Centroid location for space targets based on energy acculmulation [J]. Opt. Precision Eng., 2011, 19(12): 3043-3048. (in Chinese)[5] 海峰,袁家虎,毛羽国. 快速星图匹配算法的研究[J]. 光电工程, 1998, 25(6): 70-74. HAI F, YUAN J H, MAO Y G. Research on rapid star map matching algorithm [J]. Opto-Electronic Engineering, 1998, 25(6): 70-74. (in Chinese)[6] 张磊,魏忠慧,等. 快速全天自主星图识别[J]. 光学精密工程, 2009,17(4): 909-915. ZHANG L, WEI ZHONG H, et al.. Fast all-sky autonomous star identification [J]. Opt. Electronic Eng., 2009,17(4): 909-915. (in Chinese)[7] 张磊,何昕,等. 三角形星图识别算法的改进[J]. 光学精密工程, 2010, 18(2): 458-463. ZHANG L, HE X, et al.. Modification of triangle identification algorithm [J]. Opt. Electronic Eng., 2010, 18(2): 458-463. (in Chinese)[8] 王海涌,费峥红,张超. 改进的基于主星的星图识别算法[J]. 光学精密工程, 2009, 17(1): 220-224. WANG H Y, FEI H, ZHANG CH. An improved star pattern identification algorithm based on main star [J]. Opt. Precision Eng., 2009, 17(1): 220-224. (in Chinese)[9] 刘朝山,马瑞萍. 星图匹配制导中的关键技术[J]. 宇航学报, 2006, 27(1): 31-35. LIU CH SH, MAR R P. Star pattern matching for celestial guidance[J]. Journal of Astronautics, 2006, 27(1): 31-35. (in Chinese)[10] JAVIER R, PATRICIO L, PABLO Z. Applying SIFT Descriptors to Stellar Image Matching. CIARP 2008, LNCS 5197, 2008: 618-625.[11] LIU R, ZHANG H. Stereo cameras self-calibration based on SIFT. Proc of International Conference on Measuring Technology and Mechatronics Automation.2009: 352-355.[12] 江泽涛,吴文欢. 基于本质矩阵的摄像机自标定方法[J]. 中国图象图形学报, 2010, 15(4):565-569. JIANG Z T, WU W H. An essential matrix-based camera self-calibration method [J]. Journal of Image and Graphics, 2010, 15(4):565-569. (in Chinese)[13] 雷成,胡占义. 一种基于新的基于Kruppa方程的摄像机自标定方法[J]. 计算机学报, 2003, 26(5): 587-597. LEI CH, HU ZH Y, et al.. A novel camera self-calibration technique based on the Kruppa equations[J]. Chinese Journal of Computers, 2003, 26(5): 587-597. (in Chinese)[14] LOWE D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004:91-110.[15] HERBERT B, ANDREAS E, TINNE T, et al.. Speeded up robust features [J]. Computer Vision and Image Understanding, 2008,110(3):346-359.[16] LUO J, OUBONG G. A comparison of SIFT, PCA-SIFT, and SURF [J]. International Journal of Image Processing (IJIP),2009, 3(4): 143-152.[17] ZHAI Y, ZENG L. A SIFT matching algorithm based on adaptive contrast threshold. Proceedings of 2011 International Conference on Consumer Electronics, Communications and Networks, 2011: 1934-1937.[18] 曾峦,翟优. 基于透视投影模型的SIFT匹配方法. Proceedings of The 3rd International Conference on Computational Intelligence and Industrial Application,2010:272-276.[19] http://www.astronomyphotos.com/index.htm.

浏览量

442

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据