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...

局部时空域模型的核密度估计目标检测方法

DOI: 10.11834/jig.20120710

Keywords: 核密度估计,局部时空域模型,K均值,LBP算子

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对非参数核密度估计在前期学习阶段信息冗余和计算量大,在后期背景更新阶段自适应性差需手动调整阈值和检测结果出现阴影等问题,提出一种基于局部时空域模型的核密度估计目标检测方法。在前期训练学习阶段采用K均值聚类选择关键帧,从而避免信息冗余和计算量大问题;在后期背景更新阶段,构建一种局部时空域模型,在时间域通过历史帧信息自适应调整时间域窗口大小,在空间域利用颜色和LBP描述的纹理特征消除部分阴影问题。在复杂场景下的实验结果表明,该算法在实时性和检测准确率方面有效得到提高。

References

[1]  Nuria M O, Barbara R, Alex P P. A Bayesian computer vision system for modeling human interactions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):831-843.
[2]  Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Recognition Machine Intelligence, 2000, 22(8):747-757.
[3]  Lee D. Effective gaussian mixture learning for video background subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5):827-832.
[4]  Bai X F, Li A H, Li X L, et al. A novel background Gaussian mixture model[J]. Journal of Image and Graphics, 2011, 16(6):983-988.[白向峰,李艾华,李喜来,等. 新型背景混合高斯模型[J]. 中国图象图形学报, 2011, 16(6):983-988.]
[5]  Esfandian N, Razzazi F, Behrad A, et al. A feature selection method in spectro-temporal domain based on gaussian mixture models// Proceedings of International Conference on Signal Processing. Beijing, China: IEEE, 2010:522-525.
[6]  Jodoin P, Mignotte M, Konrad J. Statistical background subtraction using spatial cues[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(12):1758-1763.
[7]  Elgammal A, Duraisvami R, Hawood D. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J]. Proceedings of the IEEE, 2002, 90(7):1151-1163.
[8]  Xu D B, Huang L, Liu C P. Adaptive kernel density estimation for motion detection[J]. Acta Automatica Sinica, 2009, 35(4): 379-385.[徐东彬,黄磊,刘昌平.自适应核密度估计运动检测方法[J]. 自动化学报, 2009, 35(4):379-385.]
[9]  Bors A G, Nasios N. Kernel bandwidth estimation for nonparametric modeling[J]. IEEE Systems Man and Cybernetics Society, 2009, 39(6):1543-1555.
[10]  Asgharbeygi N, Maleki A. Geodesic K-means clustering //Proceedings of International conference on Pattern Recognition. Tampa, FL, USA: IEEE, 2008:1-4.
[11]  Heikkila M, Pietikainen M. A texture-based method for modeling the background and detecting moving objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):657-662.
[12]  Jong B K, Hang J. Efficient region-based motion segmentation for a video monitoring system[J]. Pattern Recognition Letters, 2003, 24(3): 113-128.
[13]  Barron J, Fleet D, Beauchemin S. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994, 12(1):42-77.
[14]  Caseiro R, Henriques J F, Batista J. Foreground segmentation via background modeling on riemannian manifolds // Proceedings of International Conference on Pattern Recognition. Istanbul, Turkey: IEEE, 2010:3570-3574.
[15]  Zhou E C, Liu C P, Zhang L Y, et al. Foreground object detection based on time information window adaptive kernel density estimation[J]. Journal on Communications, 2011, 32(3):106-115.[周恩策,刘纯平,张玲燕,等. 基于时间窗的自适应核密度估计动检测方法[J]. 通信学报, 2011, 32(3):106-115.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133