[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Color tracking with contextual switching: real-time implementation on CPU

  • Special Issue Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

The paper proposes contributions for mean-shift (MS) and covariance tracking (CT), and makes these two complementary methods cooperate. While MS runs fast and can handle non-rigid objects represented by their color distribution, CT is more time-consuming but achieves a generic tracking by mixing color and texture information. Each method is modified in order to alleviate their intrinsic limitations, and make the tracking adaptive to a changing context. Concerning MS, the colorspace is changed automatically when necessary to enhance the distinction between the object and the background. Regarding CT, the number of features is reduced without loss of accuracy, by using Local Binary Patterns. Finally, their complementary advantages are exploited in a cooperation process, which runs faster than CT alone, and is more robust than MS alone. A comprehensive study is made for their acceleration and their efficient execution on different multi-core CPUs. A speedup of ×2.8 is reached for MS and ×2.6 for CT.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. Single instruction multiple data.

  2. The reader interested in a further explanation of the colorspaces can refer to [19].

  3. A distractor is an object, the color distribution of which is approximately similar to the target object.

  4. Let us recall that the scale change is achieved in a similar fashion as [9]

  5. The detection problem is evoked in 2. In the paper, we choose to detect the object manually, in order to focus on the tracking problem.

  6. A drift appears when the accuracy of the tracking is reduced during time, and the target is progressively lost.

  7. It is a 1,600 MHz DDR3 with CAS 7—a RAM for gamer—with a 1,333 MHz nominal frequency.

  8. Typically _mm_shuffle_ps and _mm_shuffle_epi8 are used

  9. The efficiency is the speedup divided by the number of cores.

  10. This is made with _mm_shuffle_ps in SSE

  11. The scalar version requires 1 MUL, 2 LOAD, 1 STORE and the SIMD version: 7 MUL, 15 SHUFFLE, 2 LOAD, 7 STORE.

  12. 3 ADD/SUB, 4 LOAD, 1 STORE.

  13. Nvidia: https://developer.nvidia.com/cuBLAS

  14. This sequence is available here: http://info.ee.surrey.ac.uk/Personal/Z.Kalal/tld.html

References

  1. Allili, M.S., Ziou, D.: Object tracking in videos using adaptive mixture models and active contours. Neurocomput. Vision Res. Adv. Blind Signal Process. 71, 2001–2011 (2008)

  2. Babu, R.V., Pérez, P., Bouthemy, P.: Robust tracking with motion estimation and local kernel-based color modeling. Image Vision Comput. 25(8) (2007)

  3. Bak, S., Corvee, E., Brémond, F., Thonnat, M.: Person re-identification using spatial covariance regions of human body parts. In: IEEE AVSS, pp. 435–440 (2010)

  4. Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Comput. Vision Image Understand. CVIU 110(3), 346–359 (2008)

    Google Scholar 

  5. Bouchafa, S., Zavidovique, B.: C-velocity: a flow-cumulating uncalibrated approach for 3d plane detection. Int. J. Comput. Vision 97(2), 148–166 (2012)

    Google Scholar 

  6. Bouguet, J.-Y.: Pyramidal implementation of the lucas kanade feature tracker description of the algorithm. Practice 1(2), 1–9 (2000)

    Google Scholar 

  7. Castillo, S., Judd, T., Gutierrez, D.: Using eye-tracking to assess different image retargeting methods. In: Proceedings of the ACM SIGGRAPH Symposium on Applied Perception in Graphics and Visualization, APGV ’11, pp. 7–14. ACM, New York (2011)

  8. Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1631–1643 (2005)

    Google Scholar 

  9. Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–577 (2003)

    Google Scholar 

  10. Comport, A.I., Malis, E., Rives, P.: Accurate quadri-focal tracking for robust 3D visual odometry. In: IEEE International Conference on Robotics and Automation (ICRA), Rome (2007)

  11. Yang, C., Duraiswami, R., Davis, L.: Efficient mean-shift tracking via a new similarity measure. In: IEEE Computer Society, pp. 176–183 (2005)

  12. Gevers, T., Smeulders, A.W.M.: Color-based object recognition. Pattern Recognit. 32(3), 453–464 (1999)

    Google Scholar 

  13. Gouiffès, M., Laguzet, F., Lacassagne, L.: Color connectedness degree for mean shift tracking. In: International Conference on Pattern Recognition (ICPR), Istanbul (2010)

  14. Huang, D.-Y., Hu, W.-C., Hsu, M.-H.: Adaptive skin color model switching for face tracking under varying illumination. In: ICICIC, pp. 326–329 (2009)

  15. Iannizzotto, G.: Competitive combination of multiple eye detection and tracking techniques. IEEE Trans. Ind. Electron. 58(8), 3151–3159 (2011)

    Google Scholar 

  16. Ishii, I., Ichida, T., Guand, Q., Takaki, T.: 500-fps face tracking system. J. Real Time Image Process., 1–10 (2012)

  17. Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2010)

  18. Keller, C., Hermes, C., Gavrila, D.: Will the pedestrian cross? Probabilistic path prediction based on learned motion features. Pattern Recognit. 6835, 386–395 (2011)

    Google Scholar 

  19. Koschan, A., Abidi, M.A.: Digital Color Image Processing. Wiley-Interscience, New York (2008)

  20. Lacassagne, L., Manzanera, A., Dupret, A.: Motion detection: fast and robust algorithms for embedded systems. In: IEEE International Conference on Image Processing (ICIP), pp. 3265–3268 (2009)

  21. Laguzet, F., Gouiffès, M., Lacassagne, L., Etiemble, D.: Automatic color space switching for robust tracking. In: IEEE ICSIPA, pp. 295–300 (2011)

  22. Schindler, K., Gool, L.V., Leibe, B.: Coupled detection and trajectory estimation for multi-object tracking. In: International Conference on Computer Vision, pp. 115–122 (2007)

  23. Leichter, I.: Mean shift trackers with cross-bin metrics. IEEE Trans. PAMI 34(4), 695–706 (2012)

    Google Scholar 

  24. Liu, Y., Li, G., Shi, Z.: Covariance tracking via geometric particle filtering. EURASIP J. Adv. Signal Process. 2010, 1–10 (2010)

  25. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)

    Google Scholar 

  26. Montes, C., Wong, C., Ziegert, J., Mears, L.: Vision-based tracking of a dynamic target with application to multi-axis position control. J. Real Time Image Process., 1–16 (2012)

  27. Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)

    Google Scholar 

  28. Ong, E.-J., Bowden, R.: Robust facial feature tracking using shape-constrained multiresolution-selected linear predictors. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1844–1859 (2011)

    Google Scholar 

  29. Porikli, F., Tuzel, O., Meer, P.: Covariance tracking using model update based on lie algebra. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 728–735 (2006)

  30. Romero, A., Gouiffès, M., Lacassagne, L.: Feature points tracking adaptive to saturation. In: IEEE ICSIPA, pp. 277–282 (2011)

  31. Shi, J., Tomasi, C.: Good features to track. Technical report, Cornell University (1993)

  32. Song, D., Zhao, B., Tang, L.: Mean-shift algorithm fused with corner feature and color feature for target tracking. Syst. Eng. Electron. 34(1), 199–203 (2012)

    Google Scholar 

  33. Rastegar, S., Bandarabadi, M., Toopchi, Y., Ghoreishi, S.: Kernel based object tracking using metric distance transform and rvm classifier. In AJBAS (3)’09, pp. 2778–2790 (2009)

  34. Stern, H., Efros, B.: Adaptive color space switching for face tracking in multi-colored lighting environments. In: 5th IEEE International Conference on Automatic Face and Gesture Recognition, FGR ’02, p. 249 (2002)

  35. Stern, H., Efros, B.: Adaptive color space switching for tracking under varying illumination. Image Vision Comput. 23, 353–364 (2005)

    Google Scholar 

  36. Tuzel, O., Porikli, F., Meer, P.: Region covariance: a fast descriptor for detection and classification. In: ECCV 2006, vol. 3952, pp. 589–600. Springer, Berlin (2006)

  37. Tyagi, A., Davis, J.W., Potamianos, G.: Steepest descent for efficient covariance trackin. In: WMVC (2008)

  38. Vojíř, T., Matas, J.: Robustifying the flock of trackers. In: 16th Computer Vision Winter Workshop, pp. 91–97. Graz University of Technology (2011)

  39. Wang, J., Yagi, Y.: Switching local and covariance matching for efficient object tracking. In: International Conference on Pattern Recognition (ICPR) (2008)

  40. Wang, J., Yagi, Y.: Adaptive mean-shift trackingwith auxiliary particles. IEEE Trans. Syst. Man Cybern. Part B Cybern 39(6), 1578–1589 (2009)

    Google Scholar 

  41. Wu, Y., Cheng, J., Wang, J., Lu, H., Wang, J., Ling, H., Blasch, E., Bai, L.: Real-time probabilistic covariance tracking with efficient model update. IEEE Trans. Image Process. 21(5), 2824–2837 (2012)

    Google Scholar 

  42. Wu, Y., Wu, B., Liu, J., Lu, H.Q.: Probabilistic tracking on riemannian manifolds. In: International Conference on Pattern Recognition (ICPR), pp. 1–4 (2008)

Download references

Acknowledgments

This research is supported by the European ITEA2 SPY project (Surveillance imProved sYstem). Further information is available on the website: http://www.itea2-spy.org/.

Author information

Authors and Affiliations

  1. Laboratoire de Recherche en Informatique, University Paris-Sud, Paris, France

    Florence Laguzet, Andres Romero, Lionel Lacassagne & Daniel Etiemble

  2. Laboratoire d’Informatique pour la Mécanique et les Sciences de l’Ingénieur, University Paris-Sud, Paris, France

    Michèle Gouiffès

Authors
  1. Florence Laguzet
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andres Romero
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michèle Gouiffès
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lionel Lacassagne
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daniel Etiemble
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lionel Lacassagne.

Additional information

F. Laguzet and A. Romero contributed equally to the manuscript.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Laguzet, F., Romero, A., Gouiffès, M. et al. Color tracking with contextual switching: real-time implementation on CPU. J Real-Time Image Proc 10, 403–422 (2015). https://doi.org/10.1007/s11554-013-0358-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-013-0358-x

Keywords

Search

Navigation