Abstract
During matching on feature point, gray correlation matching technology is utilized to extract multi-peaks as a coarse matching set. A pair of given corresponding reference points within the left and right images is used to calculate gradients of reference difference between the reference points and each feature point within the multi-peaks set. The unique correspondence is determined by criterion of minimal gradients of reference difference. The obtained correspondence is taken as a new pair of reference points to update the reference points continuously until all feature points in the left (or right) image being matched with the right (or left) image. The gradients of reference difference can be calculated easily by means of pre-setting a pair of obvious feature points in the left and right images as a pair of corresponding reference points. Besides, the efficiency of matching can be improved greatly by taking the obtained matching point as a new pair of reference points, and by updating the reference point continuously. It is proved that the proposed algorithm is valid and reliable by 3D reconstruction on two pairs of actual natural images with abundant and weak texture, respectively.
This is a preview of subscription content, log in via an institution to check access.
References
M. Okutomi, T. Kanade, A locally adaptive window for signal matching, In: Proceedings of the Third International Conference on Computer Vision, Osaka, Japan, 1990, 190–199.
T. Kanade, M. Okutomi, A stereo matching algorithm with an adaptive window: Theory and experiment, IEEE Trans. on PAMI, 16(1994)9, 920–932.
M. J. Atallah, Faster image template matching in the sum of the absolute value of differences measure, IEEE Trans. on Image Processing, 10(2001)4, 659–663.
M. Brunig, W. Niehsen, Fast full-search block matching, IEEE Trans. on Circuits and Systems for Video Technology, 11(2001)2, 241–247.
J. J. Kweon, K. Kang, S. D. Kim, A stereo matching algorithm using line segment features, In: Fourth IEEE Region 10 International Conference, TENCON’89, Bombay, India, 1989, 589–592.
J. L. Bruyelle, J. G. Postaire, Disparity analysis for real time obstacle detection by linear stereovision, In: Proceedings of the Intelligent Vehicle’92 Symposium, Detroit, MI, USA, 1992, 51–56.
M. Pilu, A direct method for stereo correspondence based on singular value decomposition, In: Proceedings of 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, 1997, 261–266.
M. Okutomi, T. Kanade, A multiple-baseline stereo, In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Osaka, Japan, 1991, 63–69.
M. S. Lew, T. S. Huang, K. Wong, Learning and feature selection in stereo matching, IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(1994)9, 869–881.
Xiaoping Hu, N. Ahuja, Matching point features with ordered geometric, rigidity, and disparity constrains, IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(1994)10, 1041–1049.
Y. S. Chen, Y. H. Hung, C. S. Fuh, Fast block matching algorithm based on the winner-update strategy, IEEE Trans. on Image Processing, 10(2001)8, 1212–1222.
Author information
Authors and Affiliations
About this article
Cite this article
Guan, Y., Gu, W., Ye, X. et al. Gradient of reference difference based matching algorithm for image feature point. J. of Electron.(China) 21, 163–169 (2004). https://doi.org/10.1007/BF02687833
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02687833