Abstract
In this paper we address one of the fundamental topics in Computer Vision: feature detection and matching. We propose a new approach for detecting interest points on high-resolution spherical images. To achieve invariance to scale changes, points are detected across scale-space representations of images. Instead of using domain transformations or special projection approximations, we build the scale-space by solving the heat diffusion equation directly on the sphere surface. Interest points are defined as an extension of the classical Harris corner detector to the sphere. Our technique is validated on a set of real world spherical images. We perform a quantitative evaluation of our approach and obtain results that demonstrate its suitability to higher level applications, such as structure from motion and camera registration.
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
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91–110 (2004)
Hansen, P., Corke, P., Boles, W.W., Daniilidis, K.: Scale invariant feature matching with wide angle images. In: IROS, pp. 1689–1694 (2007)
Hansen, P., Corke, P., Boles, W.W., Daniilidis, K.: Scale-invariant features on the sphere. In: ICCV, pp. 1–8 (2007)
Cruz-Mota, J., Bogdanova, I., Paquier, B., Bierlaire, M., Thiran, J.P.: Scale Invariant Feature Transform on the Sphere: Theory and Applications. International Journal of Computer Vision 98, 217–241 (2012)
Bülow, T.: Multiscale image processing on the sphere. In: Van Gool, L. (ed.) DAGM 2002. LNCS, vol. 2449, pp. 609–617. Springer, Heidelberg (2002)
Bülow, T.: Spherical diffusion for 3d surface smoothing. IEEE Trans. Pattern Anal. Mach. Intell. 26, 1650–1654 (2004)
Hansen, P., Boles, W.W., Corke, P.: Spherical diffusion for scale-invariant keypoint detection in wide-angle images. In: DICTA, pp. 525–532 (2008)
Bogdanova, I., Bresson, X., Thiran, J.P., Vandergheynst, P.: Scale space analysis and active contours for omnidirectional images. Trans. Img. Proc. 16, 1888–1901 (2007)
Arican, Z., Frossard, P.: OmniSIFT: Scale Invariant Features in Omnidirectional Images. In: IEEE International Conference on Image Processing, ICIP (2010)
Puig, L., Guerrero, J.J.: Scale space for central catadioptric systems. towards a generic camera feature extractor, Barcelona, Spain (2011)
Driscoll, J., Healy, D.: Computing fourier transforms and convolutions on the 2-sphere. Advances in Applied Mathematics 15, 202–250 (1994)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vision 60, 63–86 (2004)
Lindeberg, T., Garding, J.: Shape-adapted smoothing in estimation of 3-d depth cues from affine distortions of local 2-d brightness structure. Image and Vision Computing 15, 415–434 (1997)
Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proceedings. Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 1, pp. 525–531 (2001)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004) ISBN: 0521540518
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gava, C.C., Hengen, JM., Taetz, B., Stricker, D. (2013). Keypoint Detection and Matching on High Resolution Spherical Images. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2013. Lecture Notes in Computer Science, vol 8033. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41914-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-41914-0_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41913-3
Online ISBN: 978-3-642-41914-0
eBook Packages: Computer ScienceComputer Science (R0)