基于矢量方向特征的非参数动态背景建模

doi:10.11896/j.issn.1002-137X.2016.03.054

摘要/Abstract

摘要： 针对传统的背景建模会产生空洞和阴影误检测的问题,提出了基于矢量特征的动态背景建模方法。该算法分为初始背景模型学习和更新背景模型学习两个部分。初始背景模型把图像RGB 3个特征对应到球坐标中的方向特征,并取前若干帧图片通过矢量均值聚类算法算出K个聚类,认为这K个类为这一像素点的背景模型,当一张新的图片对应像素的矢量特征落在这K类中的任何一个时,就认为其为背景；更新算法是初始模型的后续,它除了对新来的图片进行背景分析之外,也将其用来更新背景模型。该算法能够有效避免空洞现象和阴影误检测,并且当场景改变时能及时有效地更新背景。

关键词: 矢量方向特征,背景建模,矢量均值聚类,更新背景

Abstract: For the problem that the traditional background modeling results in empty hole and wrong shadow detection,we proposed a dynamic background modeling method based on vector characteristics.Learning algorithm is divided into two parts namely initial background model and updating background model.The initial background model maps the RGB feature to the direction feature in spherical coordinates.K clustering centers are calculated by the lastest images using the method of mean vector clustering algorithm,and the K clusters are considered to be the background model of the pixel.When a new image’s corresponding pixel falls into any one of the K clusters,the new pixel is considered to be background.The updating algorithm is the successor of the initial background model algorithm.Besides doing background analyse for the new image,it also uses the new image to update the background model.The algorithm can effectively reduce the empty hole and wrong shadow detection,and can update the background timely when the scene changes.

Key words: Vector direction feature,Background modeling,Mean vector clustering,Update background

蒋泳森,肖泉,王守觉. 基于矢量方向特征的非参数动态背景建模[J]. 计算机科学, 2016, 43(3): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2016.03.054

JIANG Yong-sen, XIAO Quan and WANG Shou-jue. Non-parametric Dynamic Background Modeling Based on Direction Feature of Vector[J]. Computer Science, 2016, 43(3): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2016.03.054

参考文献

[1] Friedman N,Russel S.Image segmentation in video sequence:a probabilistic approach[C]∥Proceedings of the 13^th Conference on Uncertainty in Artificial Intelligence.Providence,USA:Morgan Kaufmann,1997:175-181
[2] Stauffer C,Grimson W E L.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757
[3] Kaewtrakulpong P,Bowden R.An improved adaptive back-ground mixture model for real-time tracking with shadow detection[C]∥ Proceedings of the 2^nd European Workshop on Advanced Video Based Surveillance Systems.Providence,USA:Kluwer Academic Publishers,2001:1-5
[4] Zivkovic Z,van der Heijden F.Efficient adaptive density estimation per image pixel for the task of background subtraction[J].Pattern Recognition Letters,2006,7(7):773-780
[5] Lee D S.Effective Gaussian mixture learning for video back-ground subtraction[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,7(5):827-832
[6] Power P W,Schoonees J A.Understanding background mixture models for foreground segmentation[C]∥Proceedings of Image and Vision Computing New Zealand.Auckland,New Zealand:Auckland University Press,2002:267-271
[7] Wang Yong-zhong,Liang Yan,Pan Quan,et al.Spatiotemporal background modeling based on adaptive mixture of gauss[J].Acta Automatica Sinica,2009,35(4):371-378(in Chinese) 王永忠,梁彦,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报,2009,35(4):371-378
[8] Elgammal A,Duraiswami R,Harwood D,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J].Proceedings of the IEEE,2002,0(7):1151-1163
[9] Stenger B,Ramesh V,Paragios N,et al.Topology free hidden Markov models:application to background modeling[C]∥Proceedings of 8^th International Conference on Computer Vision.Vancouver,Canada:IEEE,2001:294-301
[10] Huo Dong-hai,Yang Dan,Zhang Xiao-hong,et al.Principal component analysis based codebook background modeling algorithm[J].Acta Automatica Sinica,2012,38(4):591-600(in Chinese) 霍东海,杨丹,张小洪,等.一种基于主成分分析的Codebook背景建模算法[J].自动化学报,2012,38(4):591-600
[11] Toyama K,Krumm J,Brumitt B,et al.Principles and practice of background maintenance[C]∥Proceedings of the 7^th International Conference on Computer Vision.Kerkyra,Greece:IEEE,1999:255-261
[12] Wang Y,Loe K F,Wu J K.A dynamic conditional random field model for foreground and shadow segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,8(2):279-289
[13] Seki M,Wada T,Fujiwara H,et al.Background subtractionbased on cooccurrence of image variations[C]∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C,USA:IEEE,2003:65-72
[14] Matsuyama T,Ohya T,Habe H.Background subtraction fornon-stationary scenes[C]∥Proceedings of the 4^th Asian Confe-rence on Computer Vision.Taipei,Taiwan:University Trier Press,2000:114-116
[15] Heikkila M,Pietikainen M.A texture-based method for mode-ling the background and detecting moving objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,8(4):657-662
[16] Chen Y T,Chen C S,Huang C R,et al.Efficient hierarchical method for background subtraction[J].Pattern Recognition,2007,0(10):2706-2715
[17] Liu Ya-zhou,Yao Hong-xun,Gao Wen,et al.NonparametricBackground Generation[C]∥International Conference on Pattern Recognition(ICPR).2006:916-919

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed