Abstract
We propose the concept of superpixel adaptive segmentation map, to produce a perceptually meaningful representation of rigid pixel image, with higher resolution of more superpixels on interesting regions according to the density distribution of desired attributes. The solution is based on the self-organizing map (SOM) algorithm, for the benefits of SOM’s ability to generate a topological map according to a probability distribution and its potential to be a natural massive parallel algorithm. We also propose the concept of parallel cellular matrix which partitions the Euclidean plane defined by input image into an appropriate number of uniform cell units. Each cell is responsible of a certain part of the data and the cluster center network, and carries out massively parallel spiral searches based on the cellular matrix topology. Experimental results from our GPU implementation show that the proposed algorithm can generate adaptive segmentation map where the distribution of superpixels reflects the gradient distribution or the disparity distribution of input image, with respect to scene topology. When the input size augments, the running time increases in a linear way with a very weak increasing coefficient.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)
Ren, X., Malik, J.: Learning a classification model for segmentation. In: 2003 Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 10–17. IEEE (2003)
Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: BVMC (2007)
Bentley, J.L., Weide, B.W., Yao, A.C.: Optimal expected-time algorithms for closest point problems. ACM Trans. Math. Softw. (TOMS) 6, 563–580 (1980)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59, 167–181 (2004)
Moore, A.P., Prince, S., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)
Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and supervoxels in an energy optimization framework. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 211–224. Springer, Heidelberg (2010)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24, 603–619 (2002)
Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008)
Vincent, L., Soille, P.: Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans. Pattern Anal. Mach. Intell. 13, 583–598 (1991)
Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: Turbopixels: fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell. 31, 2290–2297 (2009)
Weikersdorfer, D., Gossow, D., Beetz, M.: Depth-adaptive superpixels. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 2087–2090. IEEE (2012)
Hasnat, M.A., Alata, O., Trmeau, A.: Unsupervised RGB-D image segmentation using joint clustering and region merging. In: Proceedings of the British Machine Vision Conference. BMVA Press (2014)
Kohonen, T.: Self-Organizing Maps, vol. 30. Springer Science & Business Media, The Netherlands (2001)
Wang, H., Zhang, N., Creput, J.C., Moreau, J., Ruichek, Y.: Parallel structured mesh generation with disparity maps by GPU implementation. IEEE Trans. Visual Comput. Graphics 21, 1045–1057 (2015)
NVIDIA: CUDA C Programming Guide 4.2, CURAND Library, Profiler User’s Guide (2012). http://docs.nvidia.com/cuda
Sanders, J., Kandrot, E.: CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Professional, Upper Saddle River (2010)
Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: 2003 Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I-195. IEEE (2003)
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vision 92, 1–31 (2011)
Ren, C.Y., Reid, I.: gSLIC: a real-time implementation of SLIC superpixel segmentation. Technical report, Department of Engineering, University of Oxford (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, H., Mansouri, A., Créput, JC., Ruichek, Y. (2015). Massively Parallel Cellular Matrix Model for Superpixel Adaptive Segmentation Map. In: Pichardo Lagunas, O., Herrera Alcántara, O., Arroyo Figueroa, G. (eds) Advances in Artificial Intelligence and Its Applications. MICAI 2015. Lecture Notes in Computer Science(), vol 9414. Springer, Cham. https://doi.org/10.1007/978-3-319-27101-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-27101-9_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27100-2
Online ISBN: 978-3-319-27101-9
eBook Packages: Computer ScienceComputer Science (R0)