Advertisement

Robust Feature Descriptors for Efficient Vision-Based Tracking

  • Gerardo Carrera
  • Jesus Savage
  • Walterio Mayol-Cuevas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

This paper presents a robust implementation of an object tracker able to tolerate partial occlusions, rotation and scale for a variety of different objects. The objects are represented by collections of interest points which are described in a multi-resolution framework, giving a representation of those points at different scales. Inspired by [1], a stack of descriptors is built only the first time that the interest points are detected and extracted from the region of interest. This provides efficiency of representation and results in faster tracking due to the fact that it can be done off-line. An Unscented Kalman Filter (UKF) using a constant velocity model estimates the position and the scale of the object, with the uncertainty in the position and the scale obtained by the UKF, the search of the object can be constrained only in a specific region in both the image and in scale.

The use of this approach shows an improvement in real-time tracking and in the ability to recover from full occlusions.

Keywords

Object tracking Harris detector Speeded-Up Robust Features (SURF) Unscented Kalman Filter 

References

  1. 1.
    Chekhlov, D., Pupilli, M., Mayol-Cuevas, W., Calway, A.: Real-time and robust monocular slam using predictive multi-resolution descriptors. In: 2nd International Symposium on Visual Computing (November 2006)Google Scholar
  2. 2.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Computer Vision 2(60), 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 1(60), 63–86 (2004)CrossRefGoogle Scholar
  4. 4.
    Harris, C.J., Stephens, M.: A combined corner and edge detector. In: Proc. 4th Alvey Vision Conferences, pp. 147–151 (1988)Google Scholar
  5. 5.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision 2(37), 151–172 (2000)CrossRefGoogle Scholar
  6. 6.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Proceedings of the ninth European Conference on Computer Vision (May 2006)Google Scholar
  7. 7.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Transactions on Pattern Annalysis and Machine Intelligence 25, 564–577 (2003)CrossRefGoogle Scholar
  8. 8.
    Rasmussen, C., Toyama, K., Hager, G.D.: Traking objects by color alone. Technical report, Yale University (June 1996)Google Scholar
  9. 9.
    Perez, P., Hue, C., Vermaak, J., Gagnet, M.: Color-based probabilistic tracking. In: ECCV, pp. 661–675 (2002)Google Scholar
  10. 10.
    Pahlavan, K., Eklundh, J.O.: A head-eye system- analysis and design. CVGIP: Image Understanding 56, 41–56 (1992)zbMATHCrossRefGoogle Scholar
  11. 11.
    Tissainayagam, P., Suter, D.: Object tracking in image sequences using point features. Pattern Recognition 38, 105–113 (2005)CrossRefGoogle Scholar
  12. 12.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: CVPR, pp. 142–149 (2000)Google Scholar
  13. 13.
    Serby, D., Meier, E.K., Gool, L.V.: Probabilistic object tracking using multiple features. In: ICPR 2004, pp. 184–187 (2004)Google Scholar
  14. 14.
    Cipolla, R., Yamamoto, M.: Stereoscopic tracking of bodies in motion. Image and Vision Computing 8(1), 85–90 (1990)CrossRefGoogle Scholar
  15. 15.
    Blake, A., Curwen, R., Zisserman, A.: A framework for spatiotemporal control in the tracking of visual contours. Int. J. Computer Vision 11(2), 127–145 (1993)CrossRefGoogle Scholar
  16. 16.
    Blake, A., Isard, M.: Active Contours. Springer, London (1998)Google Scholar
  17. 17.
    Julier, J., Uhlmann, K.: Unscented filtering and nonlinear estimation. Proceedings of the IEEE 93, 401–422 (2004)CrossRefGoogle Scholar
  18. 18.
    Julier, S.J., Uhlmann, J.K.: A new extension of the kalman filter to nonlinear systems. In: AeroSense: The 11th Int. Symp. on Aerospace/Defence Sensing, Simulation and Controls (1997)Google Scholar
  19. 19.
    Doucet, A., Godsill, S., Andrieu, C.: On sequential monte carlo sampling methods for bayesian filtering. Statistics and Computing 10(3), 197–208 (2000)CrossRefGoogle Scholar
  20. 20.
    Perez, P., Vermaak, J., Blake, A.: Data fusion for visual tracking with particles. Proceedings of the IEEE 92, 495–513 (2004)CrossRefGoogle Scholar
  21. 21.
    Liu, J., Chen, R.: Sequential monte carlo methods for dynamic systems. American Statistical Association 93, 1032–1044 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  22. 22.
    Viola, P., Jones, M.: Rapid object detection using boosted cascade of simple features. Computer Vision and Pattern Recognition 1, 511–518 (2001)Google Scholar
  23. 23.
    Heckbert Paul, S.: Fundamentals of texture mapping and image warping. Master’s thesis, University of California, Berkeley. Dept. of Electrical Engineering and Computer Science (June 1989)Google Scholar
  24. 24.
  25. 25.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Gerardo Carrera
    • 1
  • Jesus Savage
    • 1
  • Walterio Mayol-Cuevas
    • 2
  1. 1.Universidad Nacional Autonoma de Mexico(UNAM), Department of Electrical Engineering, Bio-Robotics Laboratory, Mexico CityMexico
  2. 2.University of Bristol, Computer Science, Bristol, U.K  BS8 1UB 

Personalised recommendations