背景模型选择的目标检测Target detection based on background model selection
王俊卜,宋英磊,张冰,孙陶莹
摘要(Abstract)：
针对视频图像中的目标检测问题,提出基于模型选择的背景模型建模方法,并在此基础上实现了目标检测。该方法能够有效地根据视频图像的复杂度对其背景进行建模。对简单视频图像选择改进的均值法背景模型,对复杂视频图像则选择码本模型。以信息论中的熵和边缘比率作为依据,判断图像的复杂度,进而选择建立相应的背景模型。实验结果表明,提出的算法模型具有很好的目标检测效果,并可以较精确地处理不同复杂度的视频图像。
关键词(KeyWords)： 背景模型;码本模型;均值法;信息熵;视频图像;目标检测
基金项目(Foundation): 国家自然科学基金项目(61671222);; 江苏省特聘教授基金项目(1034901501)~~
作者(Author): 王俊卜,宋英磊,张冰,孙陶莹
DOI: 10.16652/j.issn.1004-373x.2018.13.008
参考文献(References)：
- [1]赵瑶.运动目标检测与跟踪方法研究[D].济南:山东大学,2008.ZHAO Yao.Research on moving target detection and tracking[D].Jinan:Shandong University,2008.
- [2]LI Q Z,HE D X,WANG B.Effective moving objects detection based on clustering background model for video surveillance[C]//2008 IEEE Congress on Image and Signal Processing.[S.l.]:IEEE,2008:656-660.
- [3]LIN G C,YANG S C,WANG C M,et al.Background subtraction based on codebook model and texture feature[C]//2016 IEEE International Symposium on Computer,Consumer and Control.[S.l.]:IEEE,2016:498-501.
- [4]ZHANG X,MEI C,CHEN D,et al.Feature selection in mixed data:a method using a novel fuzzy rough set-based information entropy[J].Pattern recognition,2016,56(1):1-15.
- [5]张晶,薛澄岐,沈张帆,等.基于认知分层的图像复杂度研究[J].东南大学学报(自然科学版),2016,46(6):1149-1154.ZHANG Jing,XUE Chengqi,SHEN Zhangfan,et al.Study on image complexity based on cognitive layering method[J].Journal of Southeast University(natural science),2016,46(6):1149-1154.
- [6]陈雷.基于自适应背景模型的运动目标检测[D].北京:北京交通大学,2016.CHEN Lei.Moving object based on adaptive background model[D].Beijing:Beijing Jiaotong University,2016.
- [7]张峰.复杂背景下基于分层码本模型的运动目标检测与阴影消除[D].武汉:武汉科技大学,2015.ZHANG Feng.Moving object detection and shadow elimination based on layered codebook model in complicated and dynamic scenes[D].Wuhan:Wuhan University of Science and Technology,2015.
- [8]张美静.亚像素边缘检测技术研究[D].沈阳:沈阳理工大学,2013.ZHANG Meijing.Research on sub pixel edge detection technology[D].Shenyang:Shenyang Ligong University,2013.
- [9]沈德海,侯建,鄂旭.基于改进的Sobel算子边缘检测算法[J].计算机技术与发展,2013,23(11):22-25.SHEN Dehai,HOU Jian,E Xu.Edge detection algorithm based on improved Sobel operator[J].Computer technology and development,2013,23(11):22-25.
- [10]GUO G,LAI A.A survey on still image based human action recognition[J].Pattern recognition,2014,47(10):3343-3361.