A stereo matching algorithm based on SIFT feature and homography matrix

Abstract

Aiming at the low speed of traditional scale-invariant feature transform (SIFT) matching algorithm, an improved matching algorithm is proposed in this paper. Firstly, feature points are detected and the speed of feature points matching is improved by adding epipolar constraint; then according to the matching feature points, the homography matrix is obtained by the least square method; finally, according to the homography matrix, the points in the left image can be mapped into the right image, and if the distance between the mapping point and the matching point in the right image is smaller than the threshold value, the pair of matching points is retained, otherwise discarded. Experimental results show that with the improved matching algorithm, the matching time is reduced by 73.3% and the matching points are entirely correct. In addition, the improved method is robust to rotation and translation.

Keywords

Feature Point / Match Algorithm / Sift Feature / Epipolar Line / Epipolar Constraint

References

[1] CaoM., ZhangG.M., ChenY.M.. Optik - International Journal for Light and Electron Optics, 2014, 125: 366

[2] ZhaoP., NiG.Q.. Optics and Lasers in Engineering, 2010, 48: 505

[3] ChristianB., YangN.. Procedia Computer Science, 2014, 39: 146

[4] StentoumisC., GrammatikopoulosL., KalisperakisI., KarrasG.. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 91: 29

[5] PribanicT., ObradovicN., SalviJ.. Optics Communications, 2012, 285: 1017

[6] HosniA., BleyerM., GelautzM.. Computer Vision and Image Understanding, 2013, 117: 620

[7] HuT., QiB., XuT., HeH.. Computer Vision and Image Understanding, 2012, 116: 908

[8] JiangH.Z., ZhaoH.J., LiangX.Y., LiD.. Optics and Precision Engineering, 2011, 19: 2520

[9] ZhouJ., XuY., YangX.K.. Pattern Recognition Letters, 2007, 28: 1509

[10] PloumpisS., AmanatiadisA., GasteratosA.. Image and Vision Computing, 2015, 38: 13

[11] FadaifardH., WolbergG., HaralickR.. Graphical Models, 2013, 75: 157

[12] ZhaoY.H., ChenY.Q.. Optics and Lasers in Engineering, 2013, 51: 213

[13] JiangY.L., XuY.X., LiuY.. Neurocomputing, 2013, 120: 380

[14] SongL.M., DongX.X., XiJ.T., YuY.G., YangC.K.. Optics & Laser Technology, 2013, 45: 319

[15] SongL.M., ChangY.L., LiZ.Y., WangP.Q., XingG.X., XiJ.T.. Optics Express, 2014, 22: 13641

This work has been supported by the National Natural Science Foundation of China (Nos.60808020 and 61078041), the National Science and Technology Support (No.2014BAH03F01), the Tianjin Research Program of Application Foundation and Advanced Technology (No.10JCYBJC07200), and the Technology Program of Tianjin Municipal Education Commission (No.20130324).