Anti-Occlusion Algorithm for Object Tracking Based on Multi-Feature Fusion

Abstract:

Complex background, especially when the object is similar to the background in color or the target gets blocked, can easily lead to tracking failure. Therefore, a fusion algorithm based on features confidence and similarity was proposed, it can adaptively adjust fusion strategy when occlusion occurs. And this confidence is used among occlusion detection, to overcome the problem of inaccurate occlusion determination when blocked by analogue. The experimental results show that the proposed algorithm is more robust in the case of the cover, but also has good performance under other complex scenes.

• Periodical: Applied Mechanics and Materials (Volume 610)
• Pages: 393-400
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.610.393
• Online since: August 2014
• Authors: Jie Cao, Xuan Liang*
• Keywords: Anti-Occlusion, Computer Application, Multi-Feature, Object Tracking, Particle Filter, Template Update

References

[1] Gan M G, Chen J, WANG Y N, et al. A target tracking algorithm based on mean shift and normalized moment of inertia feature [J]. Acta Automatica Sinica, 2010, 36(9): 1332-1336.

DOI: 10.3724/sp.j.1004.2010.01332

[2] Karavasilis V, Nikou C, Likas C. Visual tracking by adaptive Kalman filtering and mean shift [J]. Lecture Notes in Computer Science, Artificial Intelligence: Theories, Models and Applications, 2010, 6040: 153-162.

DOI: 10.1007/978-3-642-12842-4_19

[3] Senior A, Hampapur A, Tian Yingli, et al. Appearance models for occlusion handling [J]. Image and Vision Computing, 2006, 24(11): 1233-1243.

DOI: 10.1016/j.imavis.2005.06.007

[4] Gross R, Mattews I, Baker S. Active appearance models with occlusion [J]. Image and Vision Computing, 2006, 24(6): 593-604.

DOI: 10.1016/j.imavis.2005.08.001

[5] Khan M S, Shah M. Tracking multiple occluding people by localizing on multiple scene planes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 505-518.

DOI: 10.1109/tpami.2008.102

[6] An G C, Zhang F J, Wang H A, et al. Multi-window target tracking[J]. Journal of Computer Research and Development, 2011, 48(11): 2023-(2030).

[7] Phadke G. Robust multiple target tracking under occlusion using fragmented mean shift and Kalman filter [A]. 2011 International Conference on Communications and Signal Processing[C]. 2011, 2: 517-521.

DOI: 10.1109/iccsp.2011.5739376

[8] Yan J, Wu M Y, Chen S Z, et al. Anti-occlusion tracking algorithm based on mean shift and fragments [J]. Optics and Precision Engineering, 2010, 18(6): 1413-1419.

[9] Qi M B, Zhang L, Jiang J G, et al. Target template update method in fragment tracking [J]. Journal of Image and Graphics, 2011, 16(6): 976-982.

[10] Li Y Z, Lu Z Y, Li J. Robust video object tracking algorithm based on multi-feature fusion [J]. Journal of Xidian University, 2012, 39(4): 1-6.

[11] Fisher R. Caviar Test Case Scenarios [DB/OL]. [2011-12-05]. groups. inf. ed. ac. uk/vision/ CAVIAR/CAVIARDATA1.

[12] Birchfield S. Elliptical head tracking using intensity gra-dients and color histograms[C]/Proc of IEEE computer society conference on computer vision and pattern recognition. Santa: IEEE, 1998: 232-237.

DOI: 10.1109/cvpr.1998.698614