Abstract
In this paper, we propose a novel method for inferring image correspondences on the pair of synchronized image sequences. In the proposed method, after tracking the feature points in each image sequence over several frames, we solve the image corresponding problem from two types of geometrical constraints: (1) the motion subspace obtained from the tracked feature points of a target sequence, and (2) the epipolar constraints between the two cameras. Dissimilarly to the conventional correspondence estimation based on image matching using pixel values, the proposed approach enables us to obtain the correspondences even though the feature points, that can be seen from one camera view, but can not be seen (occluded or outside of the view) from the other camera. The validity of our method is demonstrated through the experiments using synthetic and real images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lucas, B.D., Kanade, T.: An iterative image registration technique with an approach to stereo vision. In: Image Understanding Workshop, pp. 121–130 (1981)
Freeman, W., Adelson, E.: The design and use of steerable flters. PAMI 13(9), 891–906 (1991)
Lazebnik, S., Schmid, C., Ponce, J.: Sparse texture representation using affine-invariant neighborhoods. In: CVPR, pp. 319–324 (2003)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Kanatani, K.: Motion segmentation by subspace separation and model selection. In: ICCV, vol. 2, pp. 301–306 (2001)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. IJCV 9(2), 137–154 (1992)
Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. PAMI 19(3), 206–218 (1997)
Kanatani, K.: Motion segmentation by subspace separation: Model selection and reliability evaluation. IJIG 2(2), 179–197 (2002)
Costeria, J.P., Kanade, T.: A multibody factorization method for independently moving objects. IJCV 29(3), 159–179 (1998)
Weng, J., Huang, T.S.: Complete structure and motion from two monochular sequences without stereo correspondence. In: ICPR, pp. 651–654 (1992)
Dornaika, F., Chung, R.: Stereo correspondence from motion correspondence. CVPR, 70–75 (1999)
Ho, P.K., Chung, R.: Stereo-motion with stereo and motion in complement. PAMI 22(2), 215–220 (2000)
Faugeras, O.D., Lustman, F., Toscani, G.: Motion and structure from point and line matches. In: ICCV (1987)
Zhang, Z.: Determining the epipolar geometry and its uncertainty: A review. IJCV 27(2), 161–198 (1998)
Ho, P.-K., Chung, R.: Use of affine camera model and all stereo pairs in stereo-motion. In: IEEE International Conference on Intelligent Vehicles, pp. 323–328. IEEE Computer Society Press, Los Alamitos (1998)
Fischer, M.A.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM 26(6), 381–395 (1981)
Vidal, R., Ma, Y., Sastry, S.: Generalized Principal Component Analysis (GPCA). PAMI 27(12) (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sugimoto, S., Takahashi, H., Okutomoi, M. (2007). Image Correspondence from Motion Subspace Constraint and Epipolar Constraint. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_38
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)