Color-Based Extensions to MSERs

  • Aaron Chavez
  • David Gustafson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6939)

Abstract

In this paper we present extensions to Maximally Stable Extremal Regions that incorporate color information. Our extended interest region detector produces regions that are robust with respect to illumination, background, JPEG compression, and other common sources of image noise. The algorithm can be implemented on a distributed system to run at the same speed as the MSER algorithm. Our methods are compared against a standard MSER baseline. Our approach gives comparable or improved results when tested in various scenarios from the CAVIAR standard data set for object tracking.

Keywords

Intensity Function Object Tracking Scale Invariant Feature Transform Color Function JPEG Compression 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Horn, B., Schunk, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  2. 2.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 564–575 (2003)CrossRefGoogle Scholar
  3. 3.
    Comaniciu, D., Meer, P.: Mean shift analysis and applications. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1197–1203 (1999)Google Scholar
  4. 4.
    Papageorgiou, C., Oren, M., Poggio, T.: A general framework for object detection. In: Proceedings of the Sixth IEEE International Conference on Computer Vision, pp. 555–562 (1998)Google Scholar
  5. 5.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 734–741 (2003)Google Scholar
  6. 6.
    Yilmaz, A., Javed, O., Shah, M.: Object Tracking: A Survey. ACM Journal of Computing Surveys 38(4) (2006)Google Scholar
  7. 7.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: 4th Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  8. 8.
    Lowe, D.G.: Object Recognition from Local Scale-Invariant Features. In: In Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 1, pp. 1150–1157 (1999)Google Scholar
  9. 9.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the Thirtheen British Machine Vision Conference, pp. 384–393 (2002)Google Scholar
  10. 10.
    Nistér, D., Stewénius, H.: Linear time maximally stable extremal regions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 183–196. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Forssén, P.-E., Lowe, D.: Shape descriptors for maximally stable extremal regions. In: Proceedings of the Eleventh International Conference on Computer Vision, pp. 59–73 (2007)Google Scholar
  12. 12.
    Donoser, M., Bischof, H.: Efficient maximally stable extremal region (MSER) tracking. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 553–560 (2006)Google Scholar
  13. 13.
    Forssén, P.-E.: Maximally stable colour regions for recognition and matching. In: IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, USA. IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  14. 14.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. International Journal of Computer Vision 65, 43–72 (2005)CrossRefGoogle Scholar
  15. 15.
    Wu, C.: SiftGPU: A GPU Implementation of Scale Invariant Feature Transform (2007), http://cs.unc.edu/~ccwu/siftgpu

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Aaron Chavez
    • 1
  • David Gustafson
    • 1
  1. 1.Department of Computer ScienceKansas State UniversityManhattanUSA

Personalised recommendations