Adaptive Window Strategy for High-Speed and Robust KLT Feature Tracker

  • Nirmala RamakrishnanEmail author
  • Thambipillai Srikanthan
  • Siew Kei Lam
  • Gauri Ravindra Tulsulkar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9431)


The Kanade-Lucas-Tomasi tracking (KLT) algorithm is widely used for local tracking of features. As it employs a translation model to find the feature tracks, KLT is not robust in the presence of distortions around the feature resulting in high inaccuracies in the tracks. In this paper we show that the window size in KLT must vary to adapt to the presence of distortions around each feature point in order to increase the number of useful tracks and minimize noisy ones. We propose an adaptive window size strategy for KLT that uses the KLT iterations as an indicator of the quality of the tracks to determine near-optimal window sizes, thereby significantly improving its robustness to distortions. Our evaluations with a well-known tracking dataset show that the proposed adaptive strategy outperforms the conventional fixed-window KLT in terms of robustness. In addition, compared to the well-known affine KLT, our method achieves comparable robustness at an average runtime speedup of 7x.


KLT feature tracker Robust tracker High-speed tracking 


  1. 1.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of International Joint Conference on Artificial intelligence 1981, pp. 674–679 (1981)Google Scholar
  2. 2.
    Bouguet, J.-Y.: Pyramidal implementation of the Lucas Kanade feature tracker. Intel corporation, Microprocessor research labs (2000)Google Scholar
  3. 3.
    Tanathong, S., Lee, I.: Translation-based KLT tracker under severe camera rotation using GPS/INS data. IEEE Geosci. Remote Sens. Lett. 11, 64–68 (2014)CrossRefGoogle Scholar
  4. 4.
    Gauglitz, S., Höllerer, T., Turk, M.: Evaluation of interest point detectors and feature descriptors for visual tracking. Int. J. Comput. Vis. 94, 335–360 (2011)CrossRefzbMATHGoogle Scholar
  5. 5.
    Hwangbo, M., Kim, J.-S., Kanade, T.: Inertial-aided KLT feature tracking for a moving camera. In: International Conference on Intelligent Robots and Systems, pp. 1909–1916 (2009)Google Scholar
  6. 6.
    Bouguet, J.-Y.: Pyramidal implementation of the affine Lucas Kanade feature tracker description of the algorithm. Intel Corporation (2001)Google Scholar
  7. 7.
    SanMiguel, J.C., Cavallaro, A., Martínez, J.M.: Adaptive online performance evaluation of video trackers. IEEE Trans. Image Process. 21, 2812–2823 (2012)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Forward-backward error: automatic detection of tracking failures. In: 20th International Conference on Pattern Recognition (ICPR), pp. 2756–2759 (2010)Google Scholar
  9. 9.
    Sheorey, S., Keshavamurthy, S., Yu, H., Nguyen, H., Taylor, C.N.: Uncertainty estimation for KLT tracking. In: Jawahar, C.V., Shan, S. (eds.) ACCV 2014 Workshops. LNCS, vol. 9009, pp. 475–487. Springer, Heidelberg (2015)Google Scholar
  10. 10.
    Okutomi, M., Kanade, T.: A locally adaptive window for signal matching. In: 3rd International Conference on Computer Vision, pp. 190–199 (1990)Google Scholar
  11. 11.
    Kim, J.-S., Hwangbo, M., Kanade, T.: Realtime affine-photometric KLT feature tracker on GPU in CUDA framework. In: 12th IEEE International Conference on Computer Vision Workshops, pp. 886–893 (2009)Google Scholar
  12. 12.
    Shi, J., Tomasi, C.: Good features to track. In: IEEE Computer Vision and Pattern Recognition, pp. 593–600 (1994)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Nirmala Ramakrishnan
    • 1
    Email author
  • Thambipillai Srikanthan
    • 1
  • Siew Kei Lam
    • 1
  • Gauri Ravindra Tulsulkar
    • 2
  1. 1.Nanyang Technological UniversitySingaporeSingapore
  2. 2.Manipal Institute of TechnologyManipalIndia

Personalised recommendations