一种快速多模态图像匹配导航方案
doi: 10.3724/SP.J.1146.2007.00939
A High Time-Efficiency Multi-modal Images Matching Scheme for Navigation
-
摘要: 为了能在飞行器自主导航系统中快速,精确地完成不同模态图像间的匹配,该文提出了一种基于多分辨率分析的图像匹配导航方案。这种方案采用金字塔结构,由粗到细进行匹配。在最小尺度上,采用了逐步剔除的策略,提出了边缘膨胀模板(EDT),并推导了快速算法;在中间级别上,用Hausdorff distance作为相似准则;在最后一级别上,采用交互方差进行匹配。在匹配过程中,除最小尺度上采用快速算法外,在其他匹配阶段也推导和采用了一些加速算法来减少运算量。实验结果显示该文的方法可以快速,精确地完成多模态图像匹配。另外,该文方法易于硬件实现,有助于图像匹配导航系统的工程实现。
-
关键词:
- 自主导航 /
- 图像匹配 /
- 交互方差 /
- Hausdorff 距离 /
- 多模态图像
Abstract: In this paper, a new scheme based on multi-scale is presented to match multi-modal images, in the airborne autonomous navigation system. Pyramid structure is exploited,in the scheme from coarse to fine. In the coarsest scale, a stepwise elimination scheme is introduced, the Edge Dilatation Template (EDT) is presented and some methods are introduced to reduce the calculation. In the middle scales, Hausdorff Distance (HD) is exploited as similar measure. In the finest scale, mutual variance is exploited. Some methods are also introduced and deduced to speed up the calculation in other matching scales besides the finest scale. The results of the experiments indicate that the multi-scale method can achieve fast, precision matching between multi-modal images. It can be realized by hardware easily and helps to the engineering realization of image matching navigation system. -
[1] Brown L G. A survey of image registration techniques[J].ACM Computing Surverys.1992, 24(4):325-376 [2] Candocia F. A similarity measure for stereo featurematching[J].IEEE Trans. on Image Processing.1997, 6(10):1460-1464 [3] Dai Xiaolong and Khorram S. A feature-based imageregistration algorithm using improved chain-coderepresentation combined with invariant moments[J].IEEETrans. on Geosciences and Remote Sensing.1999, 37(5):2351-2362 [4] Pluim J P W, Maintz J B A, and Viergever M A. Mutualinformation matching in multiresolution contexts[J].Imageand Vision Computing.2001, 19(1):45-52 [5] He Ren-jie and Narayana P A. Global optimization of mutualinformation: Application to three-dimensional retrospectiveregistration of magnetic resonance images[J].ComputerizedMedical Imaging and Graphics.2002, 26(4):277-292 [6] Yacov Hel-Or and Hagit Hel-Or. Real-time pattern matchingusing projection kernels[J].IEEE Trans. on Pattern Analysisand Machine Intelligence.2005, 27(9):1430-1445 [7] Huttenlocher D P, Klanderman G A, and Rucklidge W J.Comparing images using the Hausdorff distance[J].IEEETrans. on Pattern Analysis and Machine Intelligence.1993,15(10):850-863 [8] Kwon Oh-kyu, Sim Dong-gyu, and Park Rae-hong. RobustHausdorff distance matching algorithm using pyram-idalstructure[J].Pattern Recognition.2001, 34(7):2005-2013 [9] 于秋则. 合成孔径雷达(SAR)图像匹配导航技术研究. [博士论文], 华中科技大学, 2004. [10] 王东峰, 邹谋炎. 基于最大化对齐度的多模态图像自动配准[J].电子与信息学报.2003, 25(6):755-762浏览 [11] 时永刚, 刘小军, 王东峰, 等. 多模态图像配准的配准测度和性能分析[J].电子与信息学报.2004, 26(11):1706-1713浏览 [12] 李弼程,彭天强,彭波. 智能图像处理技术[M]. 北京:电子工业出版社,2004: 261-262.Li Bi-cheng, Peng Tian-qiang, and Peng Bo. Intelligent ImageProcessing Technique[M]. Beijing: Publishing House ofElectronics Industry,2004: 261-262. [13] 于秋则, 程辉, 柳建, 等. 基于改进的Hausdorff 测度和遗传算法的SAR 图像与光学图像匹配[J]. 宇航学报, 2006, 27(1):130-134 .Yu Qiu-ze, Cheng Hui, Liu Jian, et al.. Matching SAR imageto optical image using modified Hausdorff distance andgenetic algorithms[J]. Journal of Astronoutics, 2006, 27(1):130-134 .
点击查看大图
计量
- 文章访问数: 3580
- HTML全文浏览量: 116
- PDF下载量: 1131
- 被引次数: 0