计算机科学 ›› 2014, Vol. 41 ›› Issue (10): 36-41.doi: 10.11896/j.issn.1002-137X.2014.10.008
罗廷金,张军,廉蔺,徐树奎,李国辉
LUO Ting-jin,ZHANG Jun,LIAN Lin,XU Shu-kui and LI Guo-hui
摘要: 分支点是多传感器图像之间一种重要的关联特征,因此分支点匹配对多传感器图像配准有着十分重要的意义。基于CPD的基本思想提出了一致分支点漂移算法。针对分支点自身特点,提出了局部结构相容度的概念,用于度量和检验两个分支点的一致性程度;并将其作为匹配约束项嵌入到高斯混合模型分量的后验概率计算中,有效利用了分支点包含的分支边缘等结构信息,同时增强了算法对噪声和外点等干扰因素的抵抗能力,提高了分支点匹配的收敛速度。实验结果表明,提出的一致分支点漂移算法比CPD算法能够更快收敛到最优参数集上,同时得到的分支点配准精度更高。
[1] Das S,Zhang Y.Color Night Vision for Navigation and Surveillance[J].Transportation Research Record,2000,1708(1):40-46 [2] 李露,蒋宏,任章.红外与可见光复合寻的制导中的快速图像配准方法[J].哈尔滨工程大学学报,2009,30(2):228-232 [3] 李光鑫,徐抒岩,董吉洪.结构优化型颜色传递融合方法[J].电子学报,2011,39(1):213-218 [4] Wu Jian-ming,Jing Zhang-liang,et al.Study on an improvedHausdorff distance for multi-sensor image matching[J].Communications in Nonlinear Science and Numerical Simulation,2012,17(2):513-520 [5] Belongie S,Malik J,Puzicha J.Shape Matching and ObjectRecongition Using Shape Contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522 [6] Manay S,Cremers D,Hong B W,et al.Integral Invariants forShape Matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(10):1602-1618 [7] Gope C,Kehtarnavaz N.Affine Invariant Comparison of Point-Sets Using Convex Hulls and Hausdorff Distances[J].Pattern Recognition,2007,40(1):309-320 [8] Nejhum S M S,Chi Y-T,et al.Higher-Dimensional Affine Regi-stration and Vision Applications[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(7):1324-1338 [9] Heikkil J.Pattern Matching with Affine Moment Descriptors[J].Pattern Recognition,2004,37(9):1825-1834 [10] Fang Z,Tu W,et al.A Voronoi neighborhood-based search heuristic for distance/capacity constrained very large vehicle routing problems[J].International Journal of Geographical Information Science,2012,10(3):1-24 [11] Cheong O,Everett H,et al.Farthest-polygon Voronoi diagrams[J].Computational Geometry,2011,44(4):234-247 [12] Zhang Zhao-yang,et al.Spectral Feature Matching Based on Isometric Projection of Matrix[J].Applied Mechanics and Mate-rials,2011,121(6):4161-4165 [13] Besl P J,McKay N D.A Method for Registration of 3-D Shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256 [14] Chui H,Rangarajan A.A New Point Matching Algorithm forNon-Rigid Registration[J].Computer Vision and Image Understanding,2003,89(2):114-141 [15] Zheng Y F,Doermann D.Robust Point Matching for NonrigidShapes by Preserving Local Neighborhood Structures[J].IEEE Transactions on Pattem Analysis and Machine Intelligence,2006,28(4):643-649 [16] Myronenko A,Song X.Point Set Registration:Coherent Point Drift[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275 [17] Jian B,Vemuri B C.Robust Point Set Registration Using Gaus-sian Mixture Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33 (8):1633-1645 [18] Kang X,et al.Correspondenceless 3D-2D registration based on expectation conditional maximization[C]∥Progress in Biome-dical Optics And Imaging:Proceedings of SPIE,Lake Buena Vista,FL.,SPIE,2011 [19] Bishop C M.Neural Networks for Pattern Recognition[M].Oxford:Oxford University Press,1995 [20] Fischler M,Bolles.Random sample consensus:A paradigm formodel fitting with applications to image analysis and automated cartography[J].Commun.ACM,1981,24(6):35-39 [21] Zhang Jun,Luo Ting-jin,Gao Gui,et al.Junction Point Detec-tion Algorithm for SAR Image[J/OL].International Journal of Antennas and Propagation,2013 |
No related articles found! |
|