全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

融合背景权重直方图的目标跟踪

DOI: 10.11834/jig.20150108

Keywords: 目标跟踪,均值漂移,校正背景权重直方图,两层卡尔曼滤波,巴氏系数,模板更新

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的考虑到融合校正背景权重直方图(CBWH)的MeanShift(MS)目标跟踪算法只有CBWH更新而缺少目标模板更新,以及在目标遮挡时鲁棒性欠佳的不足。方法结合卡尔曼滤波器(KF)在目标状态预测和参数更新方面的可靠性,将两层KF框架融入融合CBWH的MS。第1层KF框架为目标位置预测层,通过KF噪声与巴氏系数之间的关系,实现跟踪结果的自适应调整,减少遮挡对跟踪结果的影响;第2层KF框架为目标模板更新层,通过KF对目标模板中的每个非零元素进行滤波,实现目标模板与CBWH的同步更新,减少目标特征变化对跟踪结果的影响。结果在背景干扰、遮挡以及特征变化等条件下进行实验,得到本文算法、融合CBWH的MS和传统MS的平均跟踪误差分别为5.43、19.2和51.43,显示本文算法的跟踪精度最高。同时本文算法也具有良好的实时性。结论本文算法在融合CBWH的MS基础上,加入两层KF框架,解决了原算法缺少目标模板更新和在目标遮挡时鲁棒性欠佳的不足,最后实验验证了本文算法的有效性。

References

[1]  Fukunaga K, Hostetler L D. The estimation of the gradient of a density-function with applications in pattern recognition [J]. IEEE Transactions on Information Theory, 1975, 21(1): 32-40.
[2]  Cheng Y Z. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.
[3]  Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-576.
[4]  Jeyakar J, Babu R V, Ramakrishnan K R. Robust object tracking with background-weighted local kernels [J]. Computer Vision and Image Understanding, 2008, 112(3): 296-309.
[5]  Du K, Ju Y F, Jin Y L, et al. Meanshift tracking algorithm with adaptive block color histogram [J]. Journal of Wuhan University of Technology, 2012, 34(6): 140-144.[杜凯, 巨永锋, 靳引利, 等. 自适应分块颜色直方图的mean-shift跟踪算法 [J]. 武汉理工大学学报, 2012, 34(6): 140-144.]
[6]  Bao X, Du K, Tian H. Object tracking based on improved mean shift and surf [J]. Computer Engineering and Applications, 2013, 21: 133-137.[包旭, 杜凯, 田浩. 基于改进mean shift和surf的目标跟踪 [J]. 计算机工程与应用, 2013, 21: 133-137.]
[7]  Gouiffes M, Laguzet F, Lacassagne L. Projection-histograms for mean-shift tracking[C]//Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010: 4617-4620.
[8]  Leichter I, Lindenbaum M, Rivlin E. Mean shift tracking with multiple reference color histograms [J]. Computer Vision and Image Understanding, 2010, 114(3): 400-408.
[9]  Leichter I. Mean shift trackers with cross-bin metrics [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 695-706.
[10]  Ning J F, Zhang L, Zhang D, et al. Robust mean-shift tracking with corrected background-weighted histogram [J]. Computer Vision, IET, 2012, 6(1): 62-69.
[11]  Jeyakar J, Babu R V, Ramakrishnan K R. Robust object tracking with background-weighted local kernels [J]. Computer Vision and Image Understanding, 2008, 112(3): 296-309.
[12]  Li L F, Feng Z. An efficient object tracking method based on adaptive nonparametric approach [J]. Optoelectronic Review, 2005, 13(4): 325-330.
[13]  Allen J, Xu R, Jin J S. Mean shift object tracking for a simd computer[C]//Proceedings of the 3rd International Conference on Information Technology and Applications. Sydney, Australia: IEEE, 2005, 1: 692-697.
[14]  Zhou S B, Hu P, Liu Y J. Target tracking based on improved mean-shift and adaptive kalman filter [J]. Journal of Computer Applications, 2010, 6: 1573-1576.[周尚波, 胡鹏, 柳玉炯. 基于改进mean-shift与自适应kalman滤波的视频目标跟踪 [J]. 计算机应用, 2010, 6: 1573-1576.]
[15]  Babu R V. Robust tracking with motion estimation and local kernel-based color modeling [J]. Image and Vision Computing, 2007, 25(8): 1205-1216.
[16]  Ali A, Terada K. A general framework for multi-human tracking using kalman filter and fast mean shift algorithms [J]. Journal of Universal Computer Science, 2010, 16(6): 921-937.
[17]  Li X H. Object tracking using an adaptive kalman filter combined with mean shift [J]. Optical Engineering, 2010, 49(2): 020503(1-3).
[18]  Chu C T. Human tracking by adaptive kalman filtering and multiple kernels tracking with projected gradients[C]//Proceedings of the 5th ACM/IEEE International Conference on Distributed Smart Cameras. Ghent, Belgium: IEEE, 2011: 1-6.
[19]  Chu C T. Tracking human under occlusion based on adaptive multiple kernels with projected gradients [J]. IEEE Transactions on Multimedia, 2013, 15(7):1602-1615.
[20]  Welch G, Bishop G. An introduction to the kalman filter, TR95-041 [R]. North Carolina: Department of Computer Science, University of North Carolina at Chapel Hill, 2006.
[21]  更多...
[22]  Peng N S, Yang J, Zhou D K, et al. Mean-shift tracking with adaptive model update mechanism [J]. Data Acquisition and Processing, 2005, 20(2): 126-129.[彭宁嵩, 杨杰, 周大可, 等. Mean-shift跟踪算法中目标模型的自适应更新 [J]. 数据采集与处理, 2005, 20(2): 126-129.]
[23]  Peng N S. Mean shift blob tracking with kernel histogram filtering and hypothesis testing [J]. Pattern Recognition Letters, 2005, 26(5): 605-614.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133