Skip to main content
SpringerLink
Log in

Improved DSP Matching with RPCA for Dense Correspondences

  • Conference paper
  • First Online:
Image Analysis and Recognition (ICIAR 2016)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 9730))

Included in the following conference series:

  • 2721 Accesses

Abstract

The Deformable Spatial Pyramid (DSP) matching method is popular for dense matching of images with different scenes but sharing similar semantic content, which achieves high matching accuracy. However, the warped image generated by DSP is not smooth, which mainly results from the noisy flow field by DSP. We observed the flow field could be decomposed into a low-rank term and a sparse term. Meanwhile, Robust Principle Component Analysis (RPCA) is capable of recovering the low-rank component from an observation with sparse noises. So, in this paper we propose to use RPCA to deal with the non-smoothness in DSP by recovering the low-rank term from the flow field. Experiments on VGG and LMO datasets verify that our approach obtains smoother warped image and gains higher matching accuracy than the DSP.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Barnes, C., Shechtman, E., Goldman, D.B., Finkelstein, A.: The generalized patchmatch correspondence algorithm. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 29–43. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  2. HaCohen, Y., Shechtman, E., Goldman, D.B., Lischinski, D.: Non-rigid dense correspondence with applications for image enhancement. ACM SIGGRAPH 30(4), 70:1–70:9 (2011)

    Article  Google Scholar 

  3. Liu, C., Yuen, J., Torralba, A.: Nonparametric scene parsing via label transfer. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33, 2368–2382 (2011)

    Article  Google Scholar 

  4. Karsch, K., Liu, C., Kang, S.B.: Depth extraction from video using non-parametric sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 775–788. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  5. Kim, J., Liu, C., Sha, F., Grauman, K.: Deformable spatial pyramid matching for fast dense correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2307–2314 (2013)

    Google Scholar 

  6. Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vis. (ICCV) 92(1), 1–31 (2007)

    Article  Google Scholar 

  7. Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 11:1–11:30 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  8. Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33(5), 978–994 (2011)

    Article  Google Scholar 

  9. Hassner, T., Mayzels, V., Zelnik-Manor, L.: On sifts and their scales. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1522–1528 (2012)

    Google Scholar 

  10. Qiu, W., Wang, X., Bai, X., Yuille, A.L., Tu, Z.: Scale-space SIFT flow. In: Applications of Computer Vision (WACV), pp. 1112–1119 (2014)

    Google Scholar 

  11. Tau, M., Hassner, T.: Dense correspondences across scenes and scales. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 38(5), 875–888 (2016)

    Article  Google Scholar 

  12. Hsu, K.J., Lin, Y.Y., Chuang, Y.Y.: Robust image alignment with multiple feature descriptors and matching-guided neighborhoods. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1921–1930 (2015)

    Google Scholar 

  13. Hur, J., Lim, H., Park, C., Ahn, S.C.: Generalized deformable spatial pyramid: geometry-preserving dense correspondence estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1392–1400 (2015)

    Google Scholar 

  14. Natarajan, B.K.: Sparse approximate solutions to linear systems. SIAM J. Comput. 24(2), 227–234 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  15. Candès, E.J., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theor. 52(2), 489–509 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  16. Ganesh, A., Wright, J., Li, X., Candes, E.J., Ma, Y.: Dense error correction for low-rank matrixes via principal component pursuit. In: Information Theory Proceedings (ISIT), pp. 1513–1517 (2010)

    Google Scholar 

  17. Liang, X., Ren, X., Zhang, Z., Ma, Y.: Repairing sparse low-rank texture. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 482–495. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  18. Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 27(10), 1615–1630 (2005)

    Article  Google Scholar 

Download references

Acknowledgement

This work is supported in part by National Natural Science Foundation of China under Grant No. 61175014, and the Fundamental Research Funds for the Central Universities of China.

Author information

Authors and Affiliations

  1. Department of Control Science & Engineering, Tongji University, Shanghai, China

    Fanhuai Shi & Yanli Zhang

Authors
  1. Fanhuai Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanli Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fanhuai Shi .

Editor information

Editors and Affiliations

  1. University of Porto, Porto, Portugal

    Aurélio Campilho

  2. Department of Electrical, University of Waterloo, Waterloo, Ontario, Canada

    Fakhri Karray

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Shi, F., Zhang, Y. (2016). Improved DSP Matching with RPCA for Dense Correspondences. In: Campilho, A., Karray, F. (eds) Image Analysis and Recognition. ICIAR 2016. Lecture Notes in Computer Science(), vol 9730. Springer, Cham. https://doi.org/10.1007/978-3-319-41501-7_43

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-41501-7_43

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-41500-0

  • Online ISBN: 978-3-319-41501-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation