A Comparison of Region Detectors for Tracking

  • Andreas Haja
  • Steffen Abraham
  • Bernd Jähne
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5096)


In this work, the performance of five popular region detectors is compared in the context of tracking. Firstly, conventional nearest-neighbor matching based on the similarity of region descriptors is used to assemble trajectories from unique region-to-region correspondences. Based on carefully estimated homographies between planar object surfaces in neighboring frames of an image sequence, both their localization accuracy and length, as well as the percentage of successfully tracked regions is evaluated and compared. The evaluation results serve as a supplement to existing studies and facilitate the selection of appropriate detectors suited to the requirements of a specific application. Secondly, a novel tracking method is presented, which integrates for each region all potential matches into directed multi-edge graphs. From these, trajectories are extracted using Dijkstra’s algorithm. It is shown, that the resulting localization error is significantly lower than with nearest-neighbor matching while at the same time, the percentage of tracked regions is increased.


affine-covariant region detection region tracking graph traversal performance evaluation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lowe, D.: Object recognition from local scale-invariant features. In: International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)Google Scholar
  2. 2.
    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(1/2), 43–72 (2005)CrossRefGoogle Scholar
  3. 3.
    Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3d objects. In: Tenth IEEE International Conference on Computer Vision, vol. 1 (2005)Google Scholar
  4. 4.
    Sethi, I., Jain, R.: Finding trajectories of feature points in a monocular image sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(1), 56–73 (1987)CrossRefGoogle Scholar
  5. 5.
    Dijkstra, E.: A Note on Two Problems in Connexion with Graphs. Numerische Mathematik 1(1), 269–271 (1959)CrossRefMathSciNetzbMATHGoogle Scholar
  6. 6.
    Tuytelaars, T., Van Gool, L.: Matching Widely Separated Views Based on Affine Invariant Regions. International Journal of Computer Vision 59(1), 61–85 (2004)CrossRefGoogle Scholar
  7. 7.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the British Machine Vision Conference, vol. 1, pp. 384–393 (2002)Google Scholar
  8. 8.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)CrossRefGoogle Scholar
  9. 9.
    Baumberg, A.: Reliable feature matching across widely separated views. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 774–781 (2000)Google Scholar
  10. 10.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  11. 11.
    Chetverikov, D., Verestóy, J.: Feature point tracking for incomplete trajectories. In: Proc. Int. Conf. on Computer Vision, vol. 62(4), pp. 321–338 (1999)Google Scholar
  12. 12.
    Veenman, C., Reinders, M., Backer, E.: Resolving motion correspondence for densely moving points. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(1), 54–72 (2001)CrossRefGoogle Scholar
  13. 13.
    Kadir, T., Zisserman, A., Brady, M.: An affine invariant salient region detector. In: European Conference on Computer Vision, vol. 1, pp. 228–241 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Andreas Haja
    • 1
    • 2
  • Steffen Abraham
    • 2
  • Bernd Jähne
    • 1
  1. 1.Interdisciplinary Center for Scientific ComputingUniversity of HeidelbergHeidelbergGermany
  2. 2.Robert Bosch GmbH, Corporate ResearchHildesheimGermany

Personalised recommendations