Abstract
A recent study (Int. J. Comput. Vis. 73(3), 263–284, 2007) has shown that none of the detector/descriptor combinations perform well when the camera viewpoint is changed with more than 25–30°. In this paper we introduce an efficient two-step method that increases significantly the number of correct matches of wide separated views of a given 3D scenes. First, a few kernel correspondences are identified in the images and then, based on their neighbor information, the geometric distortion that relates the surrounding regions of these seed keypoints is estimated iteratively. Next, based on these estimated parameters combined with a rough segmentation that reduces the searching space of the keypoint descriptors, the neighbor regions around every keypoint are warped accordingly. In our experiments the method has been tested extensively, yielding promising results over a wide range of viewpoints of known 3D models images.
Similar content being viewed by others
References
Abdel-Hakim, A.E., Farag, A.A.: CSIFT A SIFT descriptor with color invariant characteristics. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR) (2006)
Ancuti, C., Ancuti, C.O., Bekaert, P.: Robust matching of images across large viewpoint changes. In: Proc. of 8th International Conference on Visualization, Imaging and Image Processing, Palma De Mallorca (2008)
Baumberg, A.: Reliable feature matching across widely separated views. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR) (2000)
Beis, J., Lowe, D.G.: Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR) (1997)
Comaniciu, D., Meer, P.: Mean shift, a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)
Dufournaud, Y., Schmid, C., Horaud, R.: Matching images with different resolutions. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR), pp. 612–618 (2000)
Forssén, P.-E., Lowe, D.: Shape descriptors for maximally stable extremal regions. In: Proc. of the IEEE Conf. on Comp. Vision (ICCV) (2007)
Harris, C.G., Stephens, M.: A combined corner and edge detector. In: Proceedings of Fourth Alvey Vision Conf., vol. 18, pp. 147–151 (1988)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge Univ. Press, Cambridge (2003)
Ke, Y., Sukthankar, R.: PCA-SIFT, a more distinctive representation for local image descriptors. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR) (2004)
Lindeberg, T., Garding, J.: Shape-adapted smoothing in estimation of 3-d shape cues from affine deformations of local 2-d brightness structure. Image Vis. Comput. 15(6), 415–434 (1997)
Lindeberg, T., Garding, J.: Feature detection with automatic scale selection. Int. J. Comput. Vis. 30(2), 77–116 (1999)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Matas, J., Chum, O., Martin, U., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. of British Machine Vision Conference (BMVC), vol. 1, pp. 384–393 (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR), vol. 30, Nr. 2, pp. 257–263 (2004)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vis. 60(1), 63–86 (2004)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. Int. J. Comput. Vis. (2005)
Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3D objects. Int. J. Comput. Vis. 73(3), 263–284 (2007)
Pritchett, P., Zisserman, A.: Wide baseline stereo matching. In: Proc. of the IEEE Conf. on Comp. Vision (ICCV), pp. 754–761 (1998)
Schaffalitzky, F., Zisserman, A.: Viewpoint invariant texture matching and wide baseline stereo. In: Proc. of the IEEE Conf. on Comp. Vision (ICCV) (2001)
Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 19(5), 530–535 (1997)
Shi, J., Tomasi, C.: Good features to track. In: Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR) (1994)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Proc. of the IEEE Conf. on Comp. Vision (ICCV) (1998)
Tuytelaars, T., Van Gool, L.: Matching widely separated views based on affine invariant regions. Int. J. Comput. Vis. 59(1), 61–85 (2004)
Xiao, J., Shah, M.: Two-frame wide baseline matching. In: Proc. of the IEEE Conf. on Comp. Vision (ICCV) (2003)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ancuti, C., Ancuti, C.O. & Bekaert, P. An efficient two steps algorithm for wide baseline image matching. Vis Comput 25, 677–686 (2009). https://doi.org/10.1007/s00371-009-0353-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-009-0353-1