Abstract
We explore the performance of the recently proposed two-view image matching algorithms using affine view synthesis – ASIFT (Morel and Yu, 2009) [14] and MODS (Mishkin, Perdoch and Matas, 2013) [10] on images of objects that do not have significant local texture and that are locally not well approximated by planes.
Experiments show that view synthesis improves matching results on images of such objects, but the number of ”useful” synthetic views is lower than for planar objects matching. The best detector for matching images of 3D objects is the Hessian-Affine in the Sparse configuration. The iterative MODS matcher performs comparably confirming it is a robust, generic method for two view matching that performs well for different types of scenes and a wide range of viewing conditions.
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
Chum, O., Werner, T., Matas, J.: Two-view geometry estimation unaffected by a dominant plane. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 01, pp. 772–779. IEEE Computer Society, Washington, DC (2005)
Dahl, A.L., Aanaes, H., Pedersen, K.S.: Finding the best feature detector-descriptor combination. In: Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011, pp. 318–325. IEEE Computer Society, Washington, DC (2011)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004)
Lebeda, K., Matas, J., Chum, O.: Fixing the Locally Optimized RANSAC. In: Proceedings of the British Machine Vision Conference, pp. 1013–1023 (2012)
Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1465–1479 (2006)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 20, 91–110 (2004)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extrema regions. In: Proceedings of the British Machine Vision Conference, pp. 384–393 (2002)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. Int. J. Comput. Vision 65(1-2), 43–72 (2005)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vision 60, 63–86 (2004)
Mishkin, D., Perdoch, M., Matas, J.: Two-view matching with view synthesis revisited. In: Proceedings of the 28th Conference on Image and Vision Computing, New Zealand (2013)
Moisan, L., Stival, B.: A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix. Int. J. Comput. Vision 57(3), 201–218 (2004)
Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3d objects. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, pp. 800–807 (2005)
Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3d objects. Int. J. Comput. Vision 73(3), 263–284 (2007)
Morel, J.M., Yu, G.: ASIFT: A new framework for fully affine invariant image comparison. SIAM J. Img. Sci. 2(2), 438–469 (2009)
Muja, M., Lowe, D.: Fast approximate nearest neighbors with automatic algorithm configuration. In: VISAPP International Conference on Computer Vision Theory and Applications, pp. 331–340 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Mishkin, D., Matas, J. (2014). Matching of Images of Non-planar Objects with View Synthesis. In: Geffert, V., Preneel, B., Rovan, B., Štuller, J., Tjoa, A.M. (eds) SOFSEM 2014: Theory and Practice of Computer Science. SOFSEM 2014. Lecture Notes in Computer Science, vol 8327. Springer, Cham. https://doi.org/10.1007/978-3-319-04298-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-04298-5_4
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04297-8
Online ISBN: 978-3-319-04298-5
eBook Packages: Computer ScienceComputer Science (R0)