On the Influence of Superpixel Methods for Image Parsing

Johann Strassburg, Rene Grzeszick, Leonard Rothacker, Gernot A. Fink

2015

Abstract

Image parsing describes a very fine grained analysis of natural scene images, where each pixel is assigned a label describing the object or part of the scene it belongs to. This analysis is a keystone to a wide range of applications that could benefit from detailed scene understanding, such as keyword based image search, sentence based image or video descriptions and even autonomous cars or robots. State-of-the art approaches in image parsing are data-driven and allow for recognizing arbitrary categories based on a knowledge transfer from similar images. As transferring labels on pixel level is tedious and noisy, more recent approaches build on the idea of segmenting a scene and transferring the information based on regions. For creating these regions the most popular approaches rely on over-segmenting the scene into superpixels. In this paper the influence of different superpixel methods will be evaluated within the well known Superparsing framework. Furthermore, a new method that computes a superpixel-like over-segmentation of an image is presented that computes regions based on edge-avoiding wavelets. The evaluation on the SIFT Flow and Barcelona dataset will show that the choice of the superpixel method is crucial for the performance of image parsing.

References

  1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., and Süsstrunk, S. (2012). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2274-282.
  2. Badino, H., Franke, U., and Pfeiffer, D. (2009). The stixel world-a compact medium level representation of the 3d-world. In Pattern Recognition, pages 51- 60. Springer.
  3. Comaniciu, D. and Meer, P. (2002). Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):603-619.
  4. Farabet, C., Couprie, C., Najman, L., and LeCun, Y. (2013). Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8):1915-1929.
  5. Fattal, R. (2009). Edge-avoiding wavelets and their applications. ACM Transactions on Graphics (TOG), 28(3):22.
  6. Felzenszwalb, P. F. and Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2):167-181.
  7. Fredman, M. L. and Willard, D. E. (1994). Transdichotomous algorithms for minimum spanning trees and shortest paths. Journal of Computer and System Sciences, 48(3):533-551.
  8. Gonzalez, R. C. and Woods, R. E. (2002). Digital image processing. Prentice Hall.
  9. Liu, C., Yuen, J., and Torralba, A. (2011). Nonparametric scene parsing via label transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2368-2382.
  10. Neubert, P. and Protzel, P. (2012). Superpixel benchmark and comparison. In Proc. Forum Bildverarbeitung.
  11. Sweldens, W. (1998). The lifting scheme: A construction of second generation wavelets. SIAM Journal on Mathematical Analysis, 29(2):511-546.
  12. Tighe, J. and Lazebnik, S. (2010). Superparsing: Scalable nonparametric image parsing with superpixels. In Proc. European Conference on Computer Vision (ECCV), pages 352-365. Springer.
  13. Tighe, J. and Lazebnik, S. (2013a). Finding things: Image parsing with regions and per-exemplar detectors. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages 3001-3008. IEEE.
  14. Tighe, J. and Lazebnik, S. (2013b). Superparsing. International Journal of Computer Vision (IJCV), 101(2):329-349.
  15. Uytterhoeven, G. and Bultheel, A. (1997). The red-black wavelet transform. TW Reports.
  16. Vedaldi, A. and Soatto, S. (2008). Quick shift and kernel methods for mode seeking. In Computer VisionECCV 2008, pages 705-718. Springer.
Download


Paper Citation


in Harvard Style

Strassburg J., Grzeszick R., Rothacker L. and Fink G. (2015). On the Influence of Superpixel Methods for Image Parsing . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 518-527. DOI: 10.5220/0005355705180527


in Bibtex Style

@conference{visapp15,
author={Johann Strassburg and Rene Grzeszick and Leonard Rothacker and Gernot A. Fink},
title={On the Influence of Superpixel Methods for Image Parsing},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={518-527},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005355705180527},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - On the Influence of Superpixel Methods for Image Parsing
SN - 978-989-758-090-1
AU - Strassburg J.
AU - Grzeszick R.
AU - Rothacker L.
AU - Fink G.
PY - 2015
SP - 518
EP - 527
DO - 10.5220/0005355705180527