对数极坐标特征指导的迭代就近点法

doi:10.11896/j.issn.1002-137X.2018.01.052

摘要/Abstract

摘要： 在多模态图像,有光照、取向及尺度或纹理变化的图像,以及宽基线图像之间通常存在大的形貌畸变。然而,当前主流推广的双自举迭代就近点法(GDB-ICP)在配准这类图对时存在困难。主要原因是,该方法利用提取的尺度不变泡点(SIFT keypoint)来引导迭代就近点法(ICP),但在大畸变图像上提取的SIFT点是不可靠的。为此,提出了一种用对数极坐标特征点(LPF)来引导迭代就近点的图像配准新方法(LPF-ICP)。实验结果表明,LPF-ICP方法成功地从Rensselaer数据组中的所有22对挑战性图对提取了可靠的LPF种子,并顺利实现了全图配准,而GDB-ICP方法则只完成了其中的19对,从而证实了LPF-ICP方法的有效性。

关键词: 图像匹配,尺度不变特征点,对数极坐标空间,立体视觉

Abstract: Images with lighting variations,rotation/optical zoom,physical changes of scene or at widely different viewpoints,can substantially change their appearance and shape when they are acquired using different modalities.Even with the state-of-the-art technology,e.g.,the generalized dual-bootstrap iterative closest point (GDB-ICP) method,it is still difficult to register those challenging images.The reason is that the GDB-ICP method uses the scale-invariant blub points (or SIFT keypoints) to drive the iterative closest point method (ICP).However,the SIFT keypoints cannot be reliably extracted from images with large appearance changes.To handle this issue,this paper proposed a novel log-polar feature guided iterative closest point (LPF-ICP) algorithm for image registration.The experimental evaluation illustrates that the LPF-ICP method can reliably extract the log-polar feature points and successfully register all the 22 ima-ge pairs contained in the Rensselaer dataset,while the GDB-ICP method only succeeds in 19 of them,thus verifying the effectiveness of the proposed method.

Key words: Image registration,Scale-invariant feature point,Log-polar space,Stereo vision

周诗豪,张云. 对数极坐标特征指导的迭代就近点法[J]. 计算机科学, 2018, 45(1): 297-306. https://doi.org/10.11896/j.issn.1002-137X.2018.01.052

ZHOU Shi-hao and ZHANG Yun. Log-polar Feature Guided Iterative Closest Point Algorithm[J]. Computer Science, 2018, 45(1): 297-306. https://doi.org/10.11896/j.issn.1002-137X.2018.01.052

参考文献

[1] BROWN M,LOWE D G.Automatic panoramic image stitching using invariant features [J].Int.J.Comput.Vis.,2007,71(1):59-73.
[2] DUFAUX F,MOSCHENI F.Motion estimation techniques fordigital TV:A review and a new contribution[J].Proc.of the IEEE,1995,83(6):858-876.
[3] LUCAS B D,KANADE T.An iterative image registration technique with an application to stereo vision [C]∥ International Conference on Artifical Intelligence.Morgan Kaufmann Publi-shers Inc.,1981:674-679.
[4] BROWN L G.A survey of image registration techniques[J].ACM Comput.Surv.,1992,24(4):325-376.
[5] BAKER S,MATTHEWS I.Lucas-Kanade 20 years on:A uni-fying framework [J].International Journal of Computer Vision,2004,56(3):221-255.
[6] HOM B K P,SCHUNCK B G.Determining optical flow[J].Ar-tif.Intell.,1981,17(1-3):185-203.
[7] MAES F,COLLIGNON A,VANDERMEULEN D,et al.Multimodality image registration by maximization of mutual information [J].IEEE Trans.Med.Imag.,1997,16(2):87-198.
[8] VIOLA P,III W M W.Alignment by maximization of mutual information [J].International Journal of Computer Vision,1997,24(2):137-154.
[9] YANG G,STEWART C V,SOFKA M,et al.Registration of challenging image pairs:initialization,estimation,and decision [J].IEEE Trans.on Pattern Anal.and Mach.Intell.,2007,29(11):1973-1989.
[10] ZOKAI S,WOLBERG G.Image registration using log-polarmappings for recovery of large-scale similarity and projective transformation [J].IEEE Trans.on Image Process.,2005,14(10):1422-1434.
[11] LOWE D.Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision,2004,60(2):91-110.
[12] HARRIS C,STEPHENS M.A combined corner and edge detector [C]∥Proc.of 4th Alvey Vision Conference.Manchester,United Kingdom:1988:147-151.
[13] CANNY J.A computational approach to edge detection [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[14] FAUGERAS O,LUONG Q T,PAPADOPOULO T.The geo-metry of multiple images [M].Cambridge,MA:MIT Press,2001:251-255.
[15] CAN A,STEWART C,ROYSAM B,et al.A feature-based,robust,hierarchical algorithm for registering pairs of images of the curved human retina [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2002,24(3):347-364.
[16] STEWART C,TSAI C L,ROYSAM B.The dual-bootstrap ite-rative closest point algorithm with application to retinal image registration [J].IEEE Trans.on Medical Imaging,2003,22(11):1379-1394.
[17] PRESS W H,TEUKOLSKY S A,VETTERLING W T,et al.Numerical recipes in C:The art of scientific computing(2^nd ed)[M].Cambridge CB2 1RP:Cambridge University Press,1992:683-688.
[18] TSAI C L,LI C Y,YANG G,et al.The edge-driven dual-bootstrap iterative closest point algorithm for registration of multimodal fluorescein angiogram sequence[J].IEEE Transactions on Medical Imaging,2010,29(3):636-649.
[19] YANG S,YANG C L.Image registration algorithm based onsparse random projection and scale-invariant feature transform[J].Acta Optica Sinica,2014,34(11):98-102.(in Chinese) 杨飒,杨春玲.基于压缩感知与尺度不变特征变换的图像配准算法[J].光学学报,2014,34(11):98-102.
[20] XU J J,ZHANG Y,ZHANG H.Fast image registration algorithm based on improved Harris-SIFT descriptor[J].Journal of Electronic Measurement and Instrumentation,2015,29(1):48-54.(in Chinese) 许佳佳,张叶,张赫.基于改进Harris-SIFT算子的快速图像配准算法[J].电子测量与仪器学报,2015,29(1):48-54.
[21] BESL P,MCKAY N.A method for registration of 3D shapes[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.
[22] ZOU X J,LIN G C,TANG Y C,et al.Sub-Pixel object-Image Registration Using Improved Iterative Closest Point Method [J].Journal of Computer-Aided Design & Computer Graphics,2016,28(8):1242-1249.(in Chinese) 邹湘军,林桂潮,唐昀超,等.改进迭代最近点法的亚像素级零件图像配准[J].计算机辅助设计与图形学学报,2016,28(8):1242-1249.
[23] DAI J L,CHEN Z Y,YE X Z.The Application of ICP Algorithm in Point Cloud Alignment [J].Journal of Image and Graphics,2007,12(3):517-521.(in Chinese) 戴静兰,陈志杨,叶修梓.ICP算法在点云配准中的应用[J].中国图象图形学报,2007,12(3):517-521.
[24] LONG J W,SHEN X J,ZANG H,et al.An Adaptive Thresholding Algorithm by Background Estimation in Gaussian Scale Space[J].Acta Automatica Sinica,2014,40(8):1773-1782.(in Chinese) 龙建武,申铉京,臧慧,等.高斯尺度空间下估计背景的自适应阈值分割算法[J].Acta Automatica Sinica,2014,40(8):1773-1782.
[25] LIU L,PENG F Y,ZHAO K,et al.Simplified SIFT algorithm for fast image matching[J].Infrared and Laser Engineering,2008,37(1):181-184.(in Chinese) 刘立,彭复员,赵坤,等.采用简化SIFT算法实现快速图像匹配[J].红外与激光工程,2008,37(1):181-184.
[26] TAO T,ZHANG Y.Detection and description of scale-invariant keypoint in log-polar space [J].Journal of Image and Graphics,2015,20(12):1639-1651.(in Chinese) 陶涛,张云.对数极坐标系下尺度不变特征点的检测与描述[J].中国图象图形学报,2015,20(12):1639-1651.
[27] MIKOLAJCZYK K,SCHMID C.Scale & affine invariant inte-rest point detectors [J].International Journal of Computer Vision,2004,60(1):63-86.
[28] HOLLAND P W,WELSCH R E.Robust regression using iteratively reweighted least-squares [J].Commun.in Statist.-Theor.and Meth.,1977,6(9):813-827.
[29] BURNHAM K P,ANDERSON D R.Model selection and infe-rence:A practical information-theoretic approach[M].Berlin,Germany:Springer,1998.
[30] HARTLEY R,ZISSERMAN A.Multiple view geometry incomputer vision[M].Cambridge,UK:Cambridge Univ.Press,2003:148-149.
[31] ZHANG Y,CHU C H.One-dimensional mapping for estimating projective transformations [J].IEEE Trans.on Image Process,2010,19(11):3049-3058.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed