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...

?相机抖动场景下的运动前景检测算法?

DOI: 10.13232/j.cnki.jnju.2015.02.002, PP. 219-226

Keywords: 前景检测,相机抖动,非参数核密度,mean-shift,信息熵

Full-Text   Cite this paper   Add to My Lib

Abstract:

?前景检测是视频监控中信息提取的关键,而相机抖动造成背景边缘的像素极易误检为前景像素,降低前景检测的精确度.为此,文中提出相机抖动场景下一种基于运动信息的前景检测算法:分析二值图像中候选前景点的运动信息,构建非参数的背景运动信息分布模型;计算候选前景的运动信息与背景模型的概率似然性,由自适应的阈值控制来确定真实前景,该自适应阈值由mean-shift及信息熵算法共同确定,可以克服单个的全局阈值对场景变化适应能力差问题;针对检测到的前景点和背景点的运动信息,采用首进首出的策略更新背景运动信息分布模型,提高模型对场景实时变化的适应性.实验结果表明,该算法具有良好的鲁棒性,能有效地检测相机抖动场景下的运动前景.

References

[1]  高凯亮,覃团发,陈跃波等.一种混合高斯背景模型下的像素分类运动目标检测方法.南京大学学报(自然科学),2011,47(2):195-200.
[2]  徐东彬,黄磊,刘昌平.自适应核密度估计运动检测方法.自动化学报,2009,35(4):379-385.
[3]  staufferc,grimsonwel.learningpatternsofactivityusingreal-timetracking.ieeetransonpatternanalysisandmachineintelligence,2000,22(8):747-757.
[4]  elgammala,harwoodd,davisl.non-parametricmodelforbackgroundsubtraction.ieeeeuropeanconferenceoncomputervision,2000:751-767
[5]  barnicho,droogenbroeckmv.vibe:auniversalbackgroundsubtractionalgorithmforvideosequences.ieeetransonimageprocessing,2011,20(6):1709-1724.
[6]  jodoinpm,konradj,saligramav,etal.motiondetectionwithanunstablecamera.ieeeinternationalconferenceimageprocess,2008:229-232.
[7]  liaojuan,dongrong,libo,etal.anon-parametricmotionmodelforforegrounddetectionincamerajitterscenes.ieeesignalprocessingletters,2014,21(6):677-681.
[8]  brahmeyb,kulkarnips.animplementationofmovingobjectdetection,trackingandcountingobjectsfortrafficsurveillancesystem.internationalconferenceoncomputationalintelligenceandcommunicationsystems,2011:143-148.
[9]  goyetten,jodoinpm,poriklif,etal.changedetection.net:anewchangedetectionbenchmarkdataset.ieeecomputersocietyconferenceoncomputervisionandpatternrecognitionworkshops,2012:1-8.
[10]  zivkovicz,vanderheijdenf.efficientadaptivedensityestimationperimagepixelforthetaskofbackgroundsubtraction.patternrecognitionletters,2006:773-780.
[11]  maddalenal,petrosinoa.aself-organizingapproachtobackgroundsubtractionforvisualsurveillanceapplications.ieeetransonimageprocessing,2008,17(7):1168-1177.
[12]  comaniciud,meerp.meanshift:arobustapproachtowardfeaturespaceanalysis.ieeetransonpatternrecognitionandmachinelearning,2002,24(5):603-619.
[13]  1stieeechangedetectionworkshop.changedetection.netvideodatabase[ol].2012-10.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133