Abstract
Dense descriptors are becoming increasingly popular in a host of tasks, such as dense image correspondence, bag-of-words image classification, and label transfer. However, the extraction of descriptors on generic image points, rather than selecting geometric features, requires rethinking how to achieve invariance to nuisance parameters. In this work we pursue invariance to occlusions and background changes by introducing segmentation information within dense feature construction. The core idea is to use the segmentation cues to downplay the features coming from image areas that are unlikely to belong to the same region as the feature point. We show how to integrate this idea with dense SIFT, as well as with the dense scale- and rotation-invariant descriptor (SID). We thereby deliver dense descriptors that are invariant to background changes, rotation, and/or scaling. We explore the merit of our technique in conjunction with large displacement motion estimation and wide-baseline stereo, and demonstrate that exploiting segmentation information yields clear improvements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We were unaware of this work when first publishing [43].
- 2.
References
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373–1396 (2003)
Berg, A.C., Malik, J.: Geometric blur for template matching. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, vol. 1. IEEE, New York (2001)
Borgefors, G.: Distance transformations in digital images. Comput. Vis. Graphics Image Process. 34(3), 344–371 (1986)
Bovik, A.C., Clark, M., Geisler, W.S.: Multichannel texture analysis using localized spatial filters. Trans. Pattern Anal. Mach. Intell. 12(1), 55–73 (1990)
Brox, T., Malik, J.: Berkeley motion segmentation dataset. http://lmb.informatik.uni-freiburg.de/resources/datasets/moseg.en.html (2010)
Casasent, D., Psaltis, D.: Position, rotation, and scale invariant optical correlation. Appl. Opt. 15(7), 1795–1799 (1976)
Deriche, R.: Using Canny’s criteria to derive a recursively implemented optimal edge detector. Int. J. Comput. Vis. 1(2), 167–187 (1987)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)
Dollár, P., Zitnick, C.L.: Structured forests for fast edge detection. In: Proceedings of the International Conference on Computer Vision, pp. 1841–1848. IEEE, New York (2013)
Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. Trans. Pattern Anal. Mach. Intell. 13(9), 891–906 (1991)
Fulkerson, B., Vedaldi, A., Soatto, S.: Localizing objects with smart dictionaries. In: European Conference on Computer Vision, pp. 179–192. Springer, New York (2008)
Hassner, T., Mayzels, V., Zelnik-Manor, L.: On SIFTs and their scales. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 1522–1528. IEEE, New York (2012)
Kokkinos, I., Yuille, A.: Scale invariance without scale selection. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE, New York (2008)
Kokkinos, I., Bronstein, M., Yuille, A.: Dense scale invariant descriptors for images and surfaces (2012). INRIA Research Report 7914
Kokkinos, I., Bronstein, M.M., Litman, R., Bronstein, A.M.: Intrinsic shape context descriptors for deformable shapes. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 159–166. IEEE, New York (2012)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. Trans. Pattern Anal. Mach. Intell. 28(10), 1568–1583 (2006)
Leordeanu, M., Sukthankar, R., Sminchisescu, C.: Efficient closed-form solution to generalized boundary detection. In: European Conference on Computer Vision, pp. 516–529. Springer, New York (2012)
Liu, C., Yuen, J., Torralba, A.: SIFT flow: Dense correspondence across scenes and its applications. Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)
Liu, K., Skibbe, H., Schmidt, T., Blein, T., Palme, K., Brox, T., Ronneberger, O.: Rotation-invariant HOG descriptors using Fourier analysis in polar and spherical coordinates. Int. J. Comput. Vis. 106(3), 342–364 (2014)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Maire, M., Arbeláez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: Proceedings of the Conference on Computer Vision and Pattern Recognition. IEEE, New York (2008)
Maire, M., Yu, S.X., Perona, P.: Object detection and segmentation from joint embedding of parts and pixels. In: Proceedings of the International Conference on Computer Vision, pp. 2142–2149. IEEE, New York (2011)
Mallat, S.: Zero-crossings of a wavelet transform. Trans. Inf. Theory 37(4), 1019–1033 (1991)
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. 65(1–2), 43–72 (2005)
Nowak, E., Jurie, F., Triggs, B.: Sampling strategies for bag-of-features image classification. In: European Conference on Computer Vision, pp. 490–503. Springer, New York (2006)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)
Porat, M., Zeevi, Y.Y.: The generalized Gabor scheme of image representation in biological and machine vision. Trans. Pattern Anal. Mach. Intell. 10(4), 452–468 (1988)
Ren, X., Malik, J.: Learning a classification model for segmentation. In: Proceedings of the International Conference on Computer Vision, pp. 10–17. IEEE, New York (2003)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D: Nonlinear Phenom. 60(1), 259–268 (1992)
Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. Trans. Pattern Anal. Mach. Intell. 19(5), 530–534 (1997)
Schmidt, U., Roth, S.: Learning rotation-aware features: from invariant priors to equivariant descriptors. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 2050–2057. IEEE, New York (2012)
Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE, New York (2007)
Shi, J., Malik, J.: Normalized cuts and image segmentation. Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)
Simonyan, K., Vedaldi, A., Zisserman, A.: Descriptor learning using convex optimisation. In: European Conference on Computer Vision, pp. 243–256. Springer, New York (2012)
Simonyan, K., Vedaldi, A., Zisserman, A.: Learning local feature descriptors using convex optimisation. Trans. Pattern Anal. Mach. Intell. 12, 25–70 (2014)
Stein, A., Hebert, M.: Incorporating background invariance into feature-based object recognition. In: Application of Computer Vision, vol. 1, pp. 37–44. IEEE, 7th IEEE Workshop on Applications of Computer Vision (WACV), New York (2005)
Strecha, C., Tuytelaars, T., Van Gool, L.: Dense matching of multiple wide-baseline views. In: Proceedings of the International Conference on Computer Vision, pp. 1194–1201. IEEE, New York (2003)
Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE, New York (2008)
Strecha, C., Bronstein, A.M., Bronstein, M.M., Fua, P.: LDA-hash: improved matching with smaller descriptors. Trans. Pattern Anal. Mach. Intell. 34(1), 66–78 (2012)
Tola, E., Lepetit, V., Fua, P.: Daisy: An efficient dense descriptor applied to wide-baseline stereo. Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Proceedings of the International Conference on Computer Vision, pp. 839–846. IEEE, New York (1998)
Tron, R., Vidal, R.: Hopkins 155 dataset. http://www.vision.jhu.edu/data.htm (2007)
Trulls, E., Kokkinos, I., Sanfeliu, A., Moreno-Noguer, F.: Dense segmentation-aware descriptors. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 2890–2897. IEEE, New York (2013)
Trulls, E., Tsogkas, S., Kokkinos, I., Sanfeliu, A., Moreno-Noguer, F.: Segmentation-aware deformable part models. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 168–175. IEEE, New York (2014)
Vedaldi, A., Fulkerson, B.: An Open and Portable Library of Computer Vision Algorithms, http://www.vlfeat.org (2008)
Winder, S., Hua, G., Brown, M.: Picking the best daisy. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 178–185. IEEE, New York (2009)
Wolberg, G., Zokai, S.: Robust image registration using log-polar transform. In: International Conference on Pattern Recognition, vol. 1, pp. 493–496. IEEE, New York (2000)
Yao, J., Cham, W.K.: 3D modeling and rendering from multiple wide-baseline images by match propagation. Signal Process. Image Commun. 21(6), 506–518 (2006)
Acknowledgements
This work has been partially funded by the Spanish Ministry of Economy and Competitiveness under project RobInstruct TIN2014-58178-R and ERA-Net Chistera project ViSen PCIN-2013-047; by EU projects AEROARMS H2020-ICT-2014-1-644271, MOBOT FP7-ICT-2011-600796, and RECONFIG FP7-ICT-600825; and by grant ANR-10-JCJC-0205 (HiCoRe).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Trulls, E., Kokkinos, I., Sanfeliu, A., Moreno-Noguer, F. (2016). Dense Segmentation-Aware Descriptors. In: Hassner, T., Liu, C. (eds) Dense Image Correspondences for Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-319-23048-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-23048-1_5
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23047-4
Online ISBN: 978-3-319-23048-1
eBook Packages: EngineeringEngineering (R0)