Skip to main content
Springer Nature Link
Log in

Graph-Based Supervoxel Computation from Iterative Spanning Forest

  • Conference paper
  • First Online:
Discrete Geometry and Mathematical Morphology (DGMM 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12708))

  • 758 Accesses

Abstract

Supervoxel segmentation leads to major improvements in video analysis since it generates simpler but meaningful primitives (i.e., supervoxels). Thanks to the flexibility of the Iterative Spanning Forest (ISF) framework and recent strategies introduced by the Dynamic Iterative Spanning Forest (DISF) for superpixel computation, we propose a new graph-based method for supervoxel generation by using iterative spanning forest framework, so-called ISF2SVX, based on a pipeline composed by four stages: (a) graph creation; (b) seed oversampling; (c) IFT-based superpixel delineation; and (d) seed set reduction. Moreover, experimental results show that ISF2SVX is capable of effectively describing the video’s color variation through its supervoxels, while being competitive for the remaining metrics considered.

The authors thank Conselho Nacional de Desenvolvimento Científico e Tecnológico – CNPq – (PQ 310075/2019-0), Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – CAPES – (Grant COFECUB 88887.191730/2018-00) and Fundação de Amparo à Pesquisa do Estado de Minas Gerais – FAPEMIG – (Grants PPM-00006-18).

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)

    Article  Google Scholar 

  2. Belém, F., Guimarães, S., Falcão, A.: Superpixel segmentation using dynamic and iterative spanning forest. Sig. Process. Lett. 27, 1440–1444 (2020)

    Article  Google Scholar 

  3. Bragantini, J., Martins, S.B., Castelo-Fernandez, C., Falcão, A.X.: Graph-based image segmentation using dynamic trees. In: Vera-Rodriguez, R., Fierrez, J., Morales, A. (eds.) CIARP 2018. LNCS, vol. 11401, pp. 470–478. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-13469-3_55

    Chapter  Google Scholar 

  4. Chen, A., Corso, J.: Propagating multi-class pixel labels throughout video frames. In: Western New York Image Processing Workshop, pp. 14–17 (2010)

    Google Scholar 

  5. Ciesielski, C., Falcão, A., Miranda, P.: Path-value functions for which Dijkstra’s algorithm returns optimal mapping. J. Math. Imag. Vis. 60(7), 1025–1036 (2018)

    Article  MathSciNet  Google Scholar 

  6. Condori, M.A., Cappabianco, F.A., Falcão, A.X., Miranda, P.A.: An extension of the differential image foresting transform and its application to superpixel generation. J. Vis. Commun. Image Represent. 71, 102748 (2020)

    Article  Google Scholar 

  7. Corso, J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., Yuille, A.: Efficient multilevel brain tumor segmentation with integrated Bayesian model classification. Trans. Med. Imag. 27(5), 629–640 (2008)

    Article  Google Scholar 

  8. Falcão, A., Stolfi, J., Lotufo, R.: The image foresting transform: theory, algorithms, and applications. Trans. Pattern Anal. Mach. Intell. 26(1), 19–29 (2004)

    Article  Google Scholar 

  9. Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)

    Article  Google Scholar 

  10. Gonçalves, H.M., de Vasconcelos, G.J., Rangel, P.R., Carvalho, M., Archilha, N.L., Spina, T.V.: cudaIFT: 180x faster image foresting transform for waterpixel estimation using CUDA. In: VISIGRAPP (4: VISAPP). pp. 395–404 (2019)

    Google Scholar 

  11. Griffin, B.A., Corso, J.J.: Video object segmentation using supervoxel-based gerrymandering (2017). arXiv:1704.05165

  12. Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp. 2141–2148. IEEE (2010)

    Google Scholar 

  13. Oneata, D., Revaud, J., Verbeek, J., Schmid, C.: Spatio-temporal object detection proposals. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 737–752. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_48

    Chapter  Google Scholar 

  14. Papon, J., Abramov, A., Schoeler, M., Worgotter, F.: Voxel cloud connectivity segmentation-supervoxels for point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2027–2034 (2013)

    Google Scholar 

  15. Paris, S., Durand, F.: A topological approach to hierarchical segmentation using mean shift. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)

    Google Scholar 

  16. Sheng, H., Zhang, X., Zhang, Y., Wu, Y., Chen, J., Xiong, Z.: Enhanced association with supervoxels in multiple hypothesis tracking. IEEE Access 7, 2107–2117 (2018)

    Article  Google Scholar 

  17. Souza, K., Araújo, A., Patrocínio, Z., Jr., Guimarães, S.: Graph-based hierarchical video segmentation based on a simple dissimilarity measure. Pattern Recogn. Lett. 47, 85–92 (2014)

    Article  Google Scholar 

  18. Tsai, D., Flagg, M., Nakazawa, A., Rehg, J.: Motion coherent tracking using multi-label MRF optimization. Int. J. Comput. Vis. 100(2), 190–202 (2012)

    Article  MathSciNet  Google Scholar 

  19. Vargas-Muñoz, J., Chowdhury, A., Alexandre, E., Galvão, F., Miranda, P., Falcão, A.: An iterative spanning forest framework for superpixel segmentation. Trans. Image Process. 28(7), 3477–3489 (2019)

    Article  MathSciNet  Google Scholar 

  20. Verdoja, F., Thomas, D., Sugimoto, A.: Fast 3d point cloud segmentation using supervoxels with geometry and color for 3d scene understanding. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 1285–1290. IEEE (2017)

    Google Scholar 

  21. Wang, B., Chen, Y., Liu, W., Qin, J., Du, Y., Han, G., He, S.: Real-time hierarchical supervoxel segmentation via a minimum spanning tree. Trans. Image Process. 29, 9665–9677 (2020)

    Article  MathSciNet  Google Scholar 

  22. Wu, F., Wen, C., Guo, Y., Wang, J., Yu, Y., Wang, C., Li, J.: Rapid localization and extraction of street light poles in mobile LiDAR point clouds: a supervoxel-based approach. IEEE Trans. Intell. Trans. Syst. 18(2), 292–305 (2016)

    Article  Google Scholar 

  23. Xu, C., Corso, J.: LibSVX: a supervoxel library and benchmark for early video processing. Int. J. Comput. Vis. 119(3), 272–290 (2016)

    Article  MathSciNet  Google Scholar 

  24. Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_45

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratory of Image and Multimedia Data Science (ImScience), Pontifical Catholic University of Minas Gerais, Belo Horizonte, 31980-110, Brazil

    Carolina Jerônimo, Zenilton K. G. Patrocínio Jr. & Silvio Jamil F. Guimarães

  2. LIGM, CNRS, ESIEE Paris, Université Gustave Eiffel, 77454, Marne-la-Vallée, France

    Sarah A. Carneiro, Laurent Najman & Silvio Jamil F. Guimarães

  3. Laboratory of Image Data Science (LIDS), University of Campinas, Campinas, 13083-852, Brazil

    Felipe Belém & Alexandre Falcão

Authors
  1. Carolina Jerônimo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Felipe Belém
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sarah A. Carneiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zenilton K. G. Patrocínio Jr.
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Laurent Najman
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alexandre Falcão
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Silvio Jamil F. Guimarães
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Silvio Jamil F. Guimarães .

Editor information

Editors and Affiliations

  1. Uppsala University, Uppsala, Sweden

    Joakim Lindblad

  2. Uppsala University, Uppsala, Sweden

    Filip Malmberg

  3. Uppsala University, Uppsala, Sweden

    Nataša Sladoje

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Jerônimo, C. et al. (2021). Graph-Based Supervoxel Computation from Iterative Spanning Forest. In: Lindblad, J., Malmberg, F., Sladoje, N. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2021. Lecture Notes in Computer Science(), vol 12708. Springer, Cham. https://doi.org/10.1007/978-3-030-76657-3_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-76657-3_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-76656-6

  • Online ISBN: 978-3-030-76657-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships