Advertisement

Evaluation of Scale-Aware Realignments of Hierarchical Image Segmentation

  • Milena M. Adão
  • Silvio Jamil Ferzoli Guimarães
  • Zenilton K. G. PatrocínioJr.Email author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11401)

Abstract

A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects may appear at different scales due to their size or to their distance from the camera. One possible solution to cope with that is to realign the hierarchy such that every region containing an object is at the same level (or scale). In this work, we explore the use of regression to predict the best scale value for given region, which is then used to realign the entire hierarchy. Experimental results are presented for two different segmentation methods; along with an analysis of the adoption of different combination of mid-level features to describe regions.

Keywords

Hierarchical image segmentation Alignment of hierarchy Regression Random forest Neural network 

References

  1. 1.
    Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2006, pp. 182–182. IEEE (2006)Google Scholar
  2. 2.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE TPAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  3. 3.
    Belo, L.S., Caetano, C.A., Patrocínio Jr., Z.K.G., Guimaãres, S.J.F.: Summarizing video sequence using a graph-based hierarchical approach. Neurocomputing 173, 1001–1016 (2016)CrossRefGoogle Scholar
  4. 4.
    Carreira, J., Sminchisescu, C.: Constrained parametric min-cuts for automatic object segmentation. In: IEEE CVPR 2010, pp. 3241–3248. IEEE (2010)Google Scholar
  5. 5.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE TPAMI 40(4), 834–848 (2018)CrossRefGoogle Scholar
  6. 6.
    Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: IEEE CVPR 2016, pp. 3640–3649 (2016)Google Scholar
  7. 7.
    Chen, Y., Dai, D., Pont-Tuset, J., Van Gool, L.: Scale-aware alignment of hierarchical image segmentation. In: IEEE CVPR 2016, pp. 364–372 (2016)Google Scholar
  8. 8.
    Cousty, J., Najman, L.: Morphological floodings and optimal cuts in hierarchies. In: IEEE ICIP 2014, pp. 4462–4466 (2014)Google Scholar
  9. 9.
    Guiges, L., Cocquerez, J., Men, H.L.: Scale-sets image analysis. IJCV 68(3), 289–317 (2006)CrossRefGoogle Scholar
  10. 10.
    Guimarães, S.J.F., Kenmochi, Y., Cousty Jr., J., Z.K.G.P., Najman, L.: Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity: the case of the Felzenszwalb-Huttenlocher method. Math. Morphol. Theory Appl. 2, 55–75 (2017)Google Scholar
  11. 11.
    Hao, Z., Liu, Y., Qin, H., Yan, J., Li, X., Hu, X.: Scale-aware face detection. In: IEEE CVPR 2017, pp. 1913–1922 (2017)Google Scholar
  12. 12.
    Jie, Z., Liang, X., Feng, J., Lu, W.F., Tay, E.H.F., Yan, S.: Scale-aware pixelwise object proposal networks. IEEE TIP 25(10), 4525–4539 (2016)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Li, J., Liang, X., Shen, S., Xu, T., Feng, J., Yan, S.: Scale-aware fast R-CNN for pedestrian detection. IEEE Trans. Multimed. 20(4), 985–996 (2018)Google Scholar
  14. 14.
    Pont-Tuset, J., Marques, F.: Supervised evaluation of image segmentation and object proposal techniques. IEEE TPAMI 38(7), 1465–1478 (2016)CrossRefGoogle Scholar
  15. 15.
    Rodrigues, F., et al.: Graph-based hierarchical video cosegmentation. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10484, pp. 15–26. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68560-1_2CrossRefGoogle Scholar
  16. 16.
    Souza, K.J.F., Araújo, A.A., Patrocínio Jr., Z.K.G., Guimarães, S.J.F.: Graph-based hierarchical video segmentation based on a simple dissimilarity measure. PRL 47, 85–92 (2014)CrossRefGoogle Scholar
  17. 17.
    Xu, C., Whitt, S., Corso, J.J.: Flattening supervoxel hierarchies by the uniform entropy slice. In: IEEE ICCV 2013, pp. 2240–2247 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Milena M. Adão
    • 1
  • Silvio Jamil Ferzoli Guimarães
    • 1
  • Zenilton K. G. PatrocínioJr.
    • 1
    Email author
  1. 1.Computer Science DepartmentPontifical Catholic University of Minas GeraisBelo HorizonteBrazil

Personalised recommendations