Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Fast superpixel segmentation by iterative edge refinement

The superpixel, as an important pre-processing technique, has been successfully used in many vision applications. Introduced is a fast superpixel method called iterative edge refinement (IER). The image was first initialised as regular grids, and then concentration was on unstable pixels and relabelling them iteratively so called unstable pixels, are edge pixels around the moving boundary. It is found that the unstable pixels decrease rapidly during the iterative process, which results in a high speed-up. Experimental results on the Berkeley BSDS500 dataset show that IER achieves a segmentation performance comparable with the state-of-the-art, and moreover, runs in real-time on a single Intel i3 CPU at 2.5 GHz.

References

    1. 1)
      • 4. Ren, X.F., Malik, J.: ‘Learning a classification model for segmentation’. IEEE Int. Conf. on Computer Vision, Nice, France, October 2003, pp. 1017.
    2. 2)
    3. 3)
      • 7. Van den Bergh, M., et al: ‘SEEDS: superpixels extracted via energy-driven sampling’. European Conf. on Computer Vision, Florence, Italy, October 2012, pp. 1326.
    4. 4)
      • 2. Fulkerson, B., et al: ‘Class segmentation and object localization with superpixel neighborhoods’. IEEE Int. Conf. Computer Vision, Kyoto, Japan, October 2009, pp. 670677.
    5. 5)
    6. 6)
      • 8. Achanta, R.: ‘Source code of SLIC Superpixels’, http://ivrg.epfl.ch/research/superpixels, accessed August 2014.
    7. 7)
      • 9. Liu, M.-Y.: ‘Source code for ERS superpixels’, http://www.umiacs.umd.edu/~mingyliu/src/, accessed August 2014.
    8. 8)
    9. 9)
      • 1. Pantofaru, C., et al: ‘Object recognition by integrating multiple image segmentations’. European Conf. on Computer Vision, Marseille, France, October 2008, pp. 481494.
    10. 10)
      • 10. Van den Bergh, M.: ‘Source code for SEEDS superpixels’, http://www.mvdblive.org/seeds/, accessed August 2014.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2014.3379
Loading

Related content

content/journals/10.1049/el.2014.3379
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address