Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Lowe, D.: Object recognition from local scale-invariant features. In: International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)
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)
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)
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)
Dijkstra, E.: A Note on Two Problems in Connexion with Graphs. Numerische Mathematik 1(1), 269–271 (1959)
Tuytelaars, T., Van Gool, L.: Matching Widely Separated Views Based on Affine Invariant Regions. International Journal of Computer Vision 59(1), 61–85 (2004)
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)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)
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)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(10), 1615–1630 (2005)
Chetverikov, D., Verestóy, J.: Feature point tracking for incomplete trajectories. In: Proc. Int. Conf. on Computer Vision, vol. 62(4), pp. 321–338 (1999)
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)
Kadir, T., Zisserman, A., Brady, M.: An affine invariant salient region detector. In: European Conference on Computer Vision, vol. 1, pp. 228–241 (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Haja, A., Abraham, S., Jähne, B. (2008). A Comparison of Region Detectors for Tracking. In: Rigoll, G. (eds) Pattern Recognition. DAGM 2008. Lecture Notes in Computer Science, vol 5096. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69321-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-69321-5_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69320-8
Online ISBN: 978-3-540-69321-5
eBook Packages: Computer ScienceComputer Science (R0)