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...

基于背景像素值频次最高假设的背景重构算法

DOI: 10.11834/jig.20080421

Keywords: 背景差法,背景重构,区域生长,运动检测

Full-Text   Cite this paper   Add to My Lib

Abstract:

背景重构是背景差分法运动检测的关键问题,为了快速地重构背景,提出了一种新的基于“背景点像素值出现频次最高”假设的背景重构算法,即先在观察时间内抽样若干帧作为训练图像序列,并用帧差法对图像进行处理得到大致运动区域,再利用区域生长法得到较完整的运动区域;然后将各抽样帧内运动区域内的点都标记为前景点,而将其余点标记为背景点;最后,统计每个背景点的不同像素值出现的频次,并选出频次最大的灰度值作为该像素点的背景灰度值。实验表明,该算法能快速有效地重构背景。

References

[1]  Jolly M P D,Lakshmanan S,Jain A K.Vehicle segmentation and classification using deformable templates[J].IEEE Transactions on Pattern Analysis and Machine InteUigent,1996,18(3):293~308.
[2]  Stauffer C,Crimson W E L.Adaptive background mixture models for eal-time tracking[A].In:Proceedings of the IEEE Computer Socie-ty Conference on Computer Vision and Pattern Recognition[C],Fort Collins,CO,USA,1999,2:246~252.
[3]  Cui Yu-wei.Research of Some Preblems About Motion Detection and Track[D].Xi\'an Northwest University,2005,15~29.[崔宇巍.运动目标检测与跟踪中有关问题的研究[D].西安:西北大学,2005,15~29.]
[4]  Kornprobst P,Deriche R,Aubert G.Image acquenee analysis via partial difference equations[J].Journal of Mathematical Imaging and Vision,1999,11(1):5~26.
[5]  Smith S M,Brady J M.ASSET-2:Real-Time motion segmentation and shape tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligent,1995,17(8):814~820.
[6]  Wei Zhi-qiang,Ji Xiao-peng,Fcng Ye-wei.A moving object detec-tion method based on self-adaptive updating of backgrnund[J].ActaElectronica Sinica,2005,33(12):2261~2264.[魏志强,纪筱鹏,冯业伟.基于自适应背景图像更新的运动目标检测方法[J].电子学报,2005,33(12):2261~2264.]
[7]  Jain R.Difference and accumulative difference pictures in dynamic scene analysis[J].Image and Vision Computing,1984,2(2):99~108.
[8]  Elgammal A,Duraiswsmi R,Harweod D,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J].Proceedings of the IEEE,2002,90(7):1151~1163.
[9]  Long W,Yang Y.Stationary background generation:An alternative to the difference of two images[J].Pattern Recognition.1990.23(12):1351~1359.
[10]  Gutchess D,Trajkonie M,Cohen-Solal E,et al.A background mod-el initialization algorithm for video surveillance[A].In:Praceedings of the 8《\'th》 IEEE International Conference on Computer Vision[C],Vancouver,Canada,2001:733~740.
[11]  Hou Zhi-qiang.A background reconstruction algorithm based on pixel intensity classification[J].Journal of Software,2005,16(9):1568~1576[候志强.基于像素灰度归类的背景重构算法[J].软件学报,2o05,16(9):1568~1576.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133