Improvement of MSAC for Estimating F and H Matrix to Filter Matching Points

doi:10.13474/j.cnki.11-2246.2018.0120

Abstract

Abstract:

Aiming at the problem of mismatching in stereo image matching,mismatches are usually eliminated by some kinds of constraint.In the multi-view geometry,fundamental matrix and homography matrix are usually used to constrain the location of the corresponding points.In this paper,an improved robust MSAC algorithm is used to estimate the fundamental matrix and homography matrix to filter the mismatches of images of different types of objects.The experimental results show that:①The improved MSAC algorithm is superior to the original algorithm;②The homography matrix is suitable for the flat area images,and its binding force is higher than fundamental matrix.The fundamental matrix is suitable for any stereo images.

Key words: MSAC, stereo images, filtering matches, fundamental matrix, homography matrix

CLC Number:

LI Cheng, WANG Renli, WANG Chenggang, MING Pingshou. Improvement of MSAC for Estimating F and H Matrix to Filter Matching Points[J]. 测绘通报, 2018, 0(4): 104-107,140.

References

[1] DUAN Y N,CHEN W,WANG M Z,et al.A Relative Radiometric Correction Method for Airborne Image Using Outdoor Calibration and Image Statistics[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(8):5164-5174.
[2] LINGER M E,GOSHTASBY A A.Aerial Image Registration for Tracking[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(4):2137-2145.
[3] YE P,LIU F,ZHAO Z.Multiple Gaussian Mixture Models for Image Registration[J],IEICE Transactions on Information and Systems,2014,97(7):1927-1929.
[4] ZARAGOZA J,CHIN T J,TRAN Q H,et al.As-projective-as-possible Image Stitching with Moving DLT[J].IEEE Conference on Computer Vision and Patlern Recognition,2013,36(7):2339-2346.
[5] TORR P H,MURRAY D W.The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix[J].International Journal of Computer Vision,1997,24(3):271-300.
[6] ZHANG Z.Determining the Epipolar Geometry and Its Uncertainty:A Review[J].International Journal of Computer Vision,1996,27(2):161-195.
[7] ROUSSEEUW P J,LEROY A M.Robust Regression and Outlier Detection[J].Wiley-Interscience,2003,31(2):260-261.
[8] HARTLEY R,ZISSERMAN A.Multiple View Geometry in Computer Vision[M].[S.l.]:Cambridge University Press,2003:159-239.
[9] TORR P H S,ZISSERMAN A.MLESAC:A New Robust Estimator with Application to Estimating Image Geometry[J].Computer Vision and Image Understanding,2000,78(1):138-156.
[10] WANG H,SUTER D.MDPE:A Very Robust Estimator for Model Fitting and Range Image Segmentation[J].International Journal of Computer Vision,2004,59(2):139-166.
[11] CHUM O,WERNER T,MATAS J.Two-View Geometry Estimation Unaffected by a Dominant Plane[J].IEEE Computer Society Conference on Computer Vision and Patlern Recognition,2005,1(1):772-779.
[12] FRAHM J M,POLLEFEYS M.RANSAC for(Quasi-)Degenerate Data (QDEGSAC)[J].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,1(1):453-460.
[13] RAGURAM R,CHUM O,POLLEFEYS M,et al.USAC:A Universal Framework for Random Sample Consensus[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(8):2022-2038.
[14] LUONG Q T,FAUGERAS O D.The Fundamental Matrix:Theory,Algorithms,and Stability Analysis[J].International Journal of Computer Vision,1996,17(1):43-75.
[15] JO G S,LEE K S,CHANDRA D,et al.RANSAC versus CS-RANSAC[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence.[S.l.]:AAAI,2015.