Advertisement

Fast Superpixel Segmentation with Deep Features

  • Mubinun Awaisu
  • Liang LiEmail author
  • Junjie Peng
  • Jiawan Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11542)

Abstract

In this paper, we propose a superpixel segmentation method which utilizes extracted deep features along with the combination of color and position information of the pixels. It is observed that the results can be improved significantly using better initial seed points. Therefore, we incorporated a one-step k-means clustering to calculate the positions of the initial seed points and applied the active search method to ensure that each pixel belongs to the right seed. The proposed method was also compared to other state-of-the-art methods quantitatively and qualitatively, and was found to produce promising results that adhere to the object boundaries better than others.

Keywords

Superpixel Deep feature extraction Active search 

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. Int. J. Comput. Vision 80(3), 300–316 (2008)CrossRefGoogle Scholar
  3. 3.
    He, S., Lau, R.W.H., Liu, W., Huang, Z., Yang, Q.: SuperCNN: a superpixelwise convolutional neural network for salient object detection. Int. J. Comput. Vision 115(3), 330–344 (2015)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Jampani, V., Sun, D., Liu, M.-Y., Yang, M.-H., Kautz, J.: Superpixel sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 363–380. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_22CrossRefGoogle Scholar
  5. 5.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  6. 6.
    Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: CVPR (2015)Google Scholar
  7. 7.
    Lu, J., Yang, H., Min, D., Do, M.N.: Patch match filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. In: CVPR (2013)Google Scholar
  8. 8.
    Stutz, D., Hermans, A., Leibe, B.: Superpixels: an evaluation of the state-of-the-art. Comput. Vis. Image Underst. 166, 1–27 (2018)CrossRefGoogle Scholar
  9. 9.
    Yan, J., Yu, Y., Zhu, X., Lei, Z., Li, S.Z.: Object detection by labeling superpixels. In: CVPR (2015)Google Scholar
  10. 10.
    Zhao, J.X., Bo, R., Hou, Q., Cheng, M.M.: FLIC: fast linear iterative clustering with active search. In: AAAI (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mubinun Awaisu
    • 1
  • Liang Li
    • 1
    • 2
    Email author
  • Junjie Peng
    • 1
  • Jiawan Zhang
    • 1
  1. 1.College of Intelligence and ComputingTianjin UniversityTianjinChina
  2. 2.Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric EngineeringChina Three Gorges UniversityYichangChina

Personalised recommendations