高鹏,王瑞荣,王培力

• 1:杭州电子科技大学生命信息与仪器工程学院

摘要(Abstract)：

以设计一种全新的背景模型算法为目标,依据图像像素特征之间的差异,使用高斯核函数获取像素特征的概率密度,统计不同区间的密度估计值,从特征池中选择适合的像素特征组成特征模板图,以输入视频流中对应位置的像素特征值作为输入量,使用支持向量机训练固定数目的像素特征值,对比分离出前景和背景。该方法应用于钱塘江涌潮检测的结果表明,F-measure值均在65%以上,鲁棒性较强;支持向量机方法选择径向核函数的识别率超过90%,运算速度较高。该方法能减少水面波动的干扰,具有较高的精度,可为河流动力特征描述提供重要工具。

关键词(KeyWords)： 最优特征选择;支持向量机;背景建模;运动目标检测;涌潮检测;钱塘江

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(61374005);; 浙江省自然科学基金项目(LY14F030022)

作者(Author): 高鹏,王瑞荣,王培力

DOI: 10.13928/j.cnki.wrahe.2017.01.008

参考文献(References)：

• [1]陈仁,刘春晶,陈东,等.有色颗粒示踪方法在推移质实验中的应用[J].水利水电技术,2015,46(11):5-9.
• [2]WREN B C,AZARBAYEJANI A,DARREL T,et al.Pfinder:Real-time tracking of human body[C]//Photonics east.International Society for Optics and Photonics.1996:780-785.
• [3]GRIMSON W E L,STAUFFER C,ROMANO R,et al.Using adaptive tracking to classify and monitor activities in a site[C]//IEEE Computer society conference on computer vision and pattern Recognition.1998:23-25.
• [4]ELGAMMAL A,DURAISWAMI R,HARWOOD D,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J].Proc IEEE,2002,90(7):1151-1163.
• [5]KATO J,WATANABE T,JOGA S,et al.An HMM-based segmentation method for traffic monitoring movies[J].IEEE transactions on pattern analysis&machine intelligence,2002,24(9):1291-1296.
• [6]BARNICH O,DROOGENBROECK M V.Vi Be:A universal background subtraction algorithm for video sequences[J].IEEE transactions on image processing,2011,20(6):1709-1724.
• [7]KIM K,CHALIDABHONGSE T H,HARWOOD D,et al.Realtime foreground-background segmentation using codebook model[J].Real-time imaging,2005,11(3):172-185.
• [8]LI L,HUANG W,GU Y H,et al.Statistical modeling of complex backgrounds for foreground object detection[J].IEEE transactions on image processing,2004,13(11):1459-1472.
• [9]SEKI M,WADA T,FUJIWARA H,et al.Background subtraction based on cooccurrence of image variations[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2003:65-65.
• [10]LI L,LEUNG M K H.Integrating intensity and texture differences for robust change detection.[J].IEEE transactions on image processing.2002,11(2):105-112.
• [11]HEIKKLAM,PIETIKAINEN M.A texture-based method for modeling the background and detecting moving objects.[J].IEEE transactions on pattern analysis&machine intelligence,2006,28(4):657-62.
• [12]LIAO S,ZHAO G,KELLOKUMPU V,et al.Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes[C]//IEEE Conference on Computer Vision&Pattern Recognition.2010:1301-1306.
• [13]HAN B,DAVIS L S.Density-based multifeature background subtraction with support vector machine[J].IEEE transactions on software engineering,2011,34(5):1017-1023.
• [14]MITTAL A,PARAGIOS N.Motion-based background subtraction using adaptive kernel density estimation[C]//IEEE Computer Society Conference on Computer Vision&Pattern Recognition.2004,Vol.2:302-309.
• [15]PARAG T,ELGAMMAL A,MITTAL A.A framework for feature selection for background subtraction[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2006,Vol.2:1916-1923.
• [16]POTTHAST C,BREITENMOSER A,SHA F,et al.Active multiview object recognition:A unifying view on online feature selection and view planning[J].Robotics&autonomous systems,2016,84:31-47.
• [17]ZHUO T,ZHANG P,ZHANG Y,et al.Deformable object tracking with spatiotemporal segmentation in big vision surveillance[J].Neurocomputing,2016,204:87-96.
• [18]OSORIO R,JUAREZ I L,PENA M,et al.Surveillance system mobile object using segmentation algorithms[J].IEEE latin america transactions,2015,13(7):2441-2446.
• [19]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural processing letters,1999,9(3):293-300.
• [20]SUYKENS J A K,BRABANTER J D,LUKAS L,et al.Weighted least squares support vector machines:robustness and sparse approximation[J].Neurocomputing,2002,48(1-4):85-105.
• [21]HAO Z,WEN W,LIU Z,et al.Real-time foreground-background segmentation using adaptive support vector machine algorithm[C]//Artificial Neural Networks-ICANN 2007,International Conference,Porto,Portugal,September 9-13,2007,proceedings.2007:603-610.
• [22]GONG M,QIAN Y,LI C.Integrated foreground segmentation and boundary matting for live videos.[J].IEEE transactions on image Processing,2015,24(4):1356-1370.
• [23]张铭,尤超,赵荥.高含沙水流脉动特征试验研究[J].水利水电技术,2016,47(11):82-88,98.
• [24]HUANG D,CAI Z,HE X,et al.A SVM embedded particle filter for multi-object detection and tracking[C]//Guidance,Navigation and Control Conference.IEEE,2015:2094-2099.