Infrared Object Tracking Algorithm Based on Online AdaBoost

Abstract:

An online AdaBoost based tracking algorithm in FLIR imagery is proposed, where tracking is formulated as a binary classification problem. The object features are selected adaptively via online boosting. And then, a strong classifier is built on the weak classifiers. The confidence map of consecutive image frame is created by the strong classifier. The object localization is realized by detecting maximum of the confidence map using mean shift. The weak classfiers are updated according to the new samples to improve the discriminative ability to the object appearance and complex scene. Experiment results verify the effectives and robustness of this tracking algorithm which can improve the tracking performance efficiently.

• Periodical: Advanced Materials Research (Volumes 443-444)
• Pages: 447-451
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.443-444.447
• Online since: January 2012
• Authors: Jun Shan Li, Fang Zhou Zhao, Ying Hong Zhu, Wei Yang
• Keywords: Adaboost, Feature Selection, FLIR, Object Tracking

References

[1] Ahamed J, Jafri M N, Ahamad J, et al. Design and implementation of a neural network for real-time object tracking[A]. Proceedings of World Academy of Science, Engineering and Technology[C]. Oslo, Norway, 2005, 209～212.

[2] Sochman J. Learning for sequential classification[D]. Prague: Czech Technical University, (2009).

[3] Bohyung H, Davis L. Object tracking by adaptive feature extraction[A]. International Conference on Image Processing[C]. Singapore, 2004, 1501～1504.

DOI: 10.1109/icip.2004.1421349

[4] Avidan S. Subset selection for efficient SVM tracking[A]. Proceedings of the 5th IEEE Intenational Conference on Automatic Face and Gesture Recognition[C]. Washington, USA, 2003, 249～254.

[5] Avidan S. Ensemble tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2): 261～271.

DOI: 10.1109/tpami.2007.35

[6] Freund Y, Schapire R. A short introduction to boosting[J]. Journal of Japanese Society for Artificial Intelligence, 1999, 14(5): 771～780.

[7] Grabner H, Grabner M, Bischof H. Real-time tracking via on-line boosting[A]. Proceedings of British Machine Vision Conference[C]. Edinburgh, 2006, 47～56.

DOI: 10.5244/c.20.6

[8] Viola P, Michael J. Rapid object detection using a boosted cascade of simple features[A]. IEEE Conference on Computer Vision and Pattern Recognition[C]. Kauai, USA, 2001, 511～518.

DOI: 10.1109/cvpr.2001.990517

[9] Yang C J, Duraiswami R, Davis L. Efficient mean shift tracking via a new similarity measure[A]. IEEE Conference on Computer Vision and Pattern Recognition[C]. San Diego, USA, 2005, 176～183.

DOI: 10.1109/cvpr.2005.139

[10] Yilmaz A, Javed O, Shah M. Object tracking: a survey[J]. ACM Computing Surveys, 2006, 38(4): 13～35.

DOI: 10.1145/1177352.1177355