Abstract
According to the mean shift tracking algorithm, weights are used to reduce the background interference. However, weights also weaken the representation of the target at the same time. In order to reduce of weakness for model representation brought by the weight, weighted fusion which is composed of target model, candidate model and the probability that the pixel belonging to foreground is proposed to enhance the difference between foreground and background. The purpose is to resist the affection brought by background pixels. Firstly, weak classifiers composed of color and texture features are deduced by Bayesian and update the weak classifiers by changing the parameters of the Gauss distribution. Projection vector to distinguish the foreground and background is found through iteration. Then the projection vector obtained by foreground probability map and weight in mean shift is fused. The projection vector that strengthens the difference between foreground and background is updated to adapt to the changes of illumination or background. Finally, the target center position, scale and rotation angle are determined to achieve the target tracking by the moment features based on the improved weight.
Similar content being viewed by others
References
Bai X, Li A, Cai Y et al (2012) Real-time objects detection method in complex scenes. J Comput Aided Des Comput Graph 24(1):104–111
Comaniciu D, Ramesh V, Meer P (2003) Kernel-based object tracking. IEEE Trans Pattern Anal Mach Intell 25(5):564–577
Grabner H, Grabner M, Bischof H (2006) Real-time tracking via on-line boosting. BMVC 1(5):47–56
Hsia KH, Lien SF, Su JP (2013) Moving target tracking based on CamShift approach and Kalman filter. Int J Appl Math Inf Sci 7(1):193–200
Jeyakar J, Babu RV, Ramakrishnan KR (2008) Robust object tracking with background-weighted local kernels. Comput Vis Image Underst 112(3):296–309
Jo YG, Lee JY, Kang H (2006) Segmentation tracking and recognition based on foreground-background absolute features, simplified SIFT, and particle filters. IEEE Congress Evol Comput:1279–1284
Lee J, Lee W, Jeong D (2003) Object tracking method using back-projection of multiple color histogram models, Circuits and Systems, 2003. ISCAS’03. In: Proceedings of the 2003 international symposium on IEEE, vol 2, no 2, pp 668–671
Leichter I (2012) Mean shift trackers with cross-bin metrics. IEEE Trans Pattern Anal Mach Intell 34(4):695–706
Li SX, Wu O, Zhu C F et al (2013) Visual object tracking using spatial context information and global tracking skills. Comput Vis Image Underst:1–15
Ning J, Zhang L, Zhang D et al (2009) Wu.Robust object tracking using joint color-texture histogram. Int J Pattern Recog Artif Intell 23(7):1245–1263
Ning J, Zhang L, Zhang D et al (2012) Scale and orientation adaptive mean shift tracking. Comput Vis IET 6(1):52–61
Ning J, Zhang L, Zhang D et al (2012) Robust mean-shift tracking with corrected background-weighted histogram. Comput Vis 6(1):62–69
Schapire R E (2003) The boosting approach to machine learning: an overview. In: Lecture notes in statistics. Springer Verlag, New York, pp 149–172
Subudhi BN, Ghosh S, Ghosh A. (2012) Object and shadow separation using fuzzy Markov random field and local gray level co-occurence matrix based textural features. In: 2012 12th international conference on intelligent systems design and applications (ISDA). IEEE, pp 95–100
Vojir T, Noskova J, Matas J (2013) Robust scale-adaptive mean-shift for tracking, image analysis. Springer, Berlin Heidelberg, pp 652–663
Wang LF, Wu HY, Pan CH (2009) Mean-Shift object tracking with a novel back-projection calculation method. In: Computer visionCACCV 2009. Springer, Berlin Heidelberg, pp 83–92
Wang L, Pan C, Xiang S (2011) Mean-shift tracking algorithm with weight fusion strategy. In: 2011 18th IEEE international conference on image processing (ICIP). IEEE, pp 473–476
Yang F, Lu H, Chen YW (2010) Robust tracking based on boosted color soft segmentation and ica-r. In: 2010 17th IEEE international conference on image processing (ICIP). IEEE, pp 3917– 3920
Yang Y, Jia Y, Rong C et al (2013) Object tracking based on corrected background-weighted histogram mean shift and Kalman filter. In: Proceedings of the 2nd international conference on systems engineering and modeling, pp 687–692
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhou, Z., Zhou, M. & Shi, X. Target tracking based on foreground probability. Multimed Tools Appl 75, 3145–3160 (2016). https://doi.org/10.1007/s11042-014-2427-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-014-2427-y