期刊文献+

一种基于三层圆柱体码本模型的前景检测算法

A Foreground Detection Algorithm Based on Three-Layers-Cylinder Codebook Model
下载PDF
导出
摘要 针对经典码本模型算法无法消除运动目标阴影和码本模型参数难以调节的问题,提出一种在YUV空间下的三层圆柱体码本模型算法。该算法根据运动阴影与背景相比色度相同亮度偏低的特点,在模型底部构建了阴影背景模型;根据光照变化的特点,在模型顶部构建高亮背景模型;并对亮度分量进行高斯建模,用以调节码本模型参数。实验结果表明:采用该模型和参数调节方法能较好的去除阴影和适应光照的变化,而且较好的检测精度和鲁棒性,适用于复杂环境下的前景检测。 Considering that the cIassic codebook modeI aIgorithm can not eIiminate the shadow of moving objects and hard to adjust the modeI parameters,a foreground detection aIgorithm based on three-Iayers-cyIinder codebook modeI is proposed. According to the characteristics that the chromaticity of moving shadow is same as that of the background and the moving shadow is Iess bright than the background,the shadow background modeI is constructed in the bottom of the modeI.Then the highIight background modeI is constructed in the top of the modeI based on the characteristics of mutation of Iumi-nance.After that,the Iuminance component is modeIed by the Gaussian modeI,in order to adjust the modeI parameters.
作者 陈鑫 章云
出处 《工业控制计算机》 2014年第9期88-89,共2页 Industrial Control Computer
关键词 前景检测 码本模型 阴影消除 foreground detection codebook modeI shadow removeI
  • 相关文献

参考文献11

  • 1RUI L, LEI Y, PENGQI G, et al. Aviation video moving-target detection with inter-frame difference [C]//3rd.lnternational Congress on Image and Signal Processing (ClSP). Yantai, China: IEEE. 2010.
  • 2ADIV G. Determining three-dimensional motion and structure from optical flow generated by several moving objects [J]. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 1985, 7(4): 384-401.
  • 3Sun H, Feng T, Tan T. Robust extraction of moving objects from image sequences[C]. Proc the Fourth Asian Conference on Computer Vision, Taiwan. 2000:961-964.
  • 4JAIN R. Difference and accumulative difference pictures in dynamic scene analysis [J]. Image and Vision Computing, 1984, 2(2): 99-108.
  • 5McKenna Setal. Tracking groups of people[J]. Computer Vi- sion and Image Understanding, 2000, 80(1): 42-56.
  • 6JAE K S, HO I J, GEN L. Mixture of gaussians-based background subtraction for bayer-pattern image sequences [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(3): 365-370.
  • 7霍东海,杨丹,张小洪,洪明坚.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. 被引量:18
  • 8郭春生,王盼.一种基于码本模型的运动目标检测算法[J].中国图象图形学报,2010,15(7):1079-1083. 被引量:12
  • 9Kim K, Chalidabhongse T H, Harwood D, Davis L. Real-time foreground-background segmentation using codebook model [J]. Real-Time Tmaging, 2005, 11(3): 172-185.
  • 10Kim K, Chalidabhongse T H, Harwood D, et al. Background modeling and subtraction by codebook construction [C]// International Conference on Image Processing. Maryland, USA, University of Maryland press, 2004.

二级参考文献8

  • 1Christopher R W, Ali A, Trevor D, et al. Pfinder: real-time tracking of the human body[ J]. IEEE Transactions on PAMI, 1997, 19(7) : 780-785.
  • 2Nir F, Stuart R. Image segmentation in video sequences: a probabilistic approach [ C ]//Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence. San Fransisco, USA:Morgan Kaufmann, 1997: 175-181.
  • 3Lucia M, Alfredo P. A self-organizing approach to background subtraction for visual surveillance applications [ J ]. IEEE Transactions on IP, 2008, 17 (7) : 1168-1177.
  • 4Kyungnam K, Thanarat H C, David H, et al. Real-time foreground-background segmentation using codebook model [ J ]. Real-Time Imaging, 2005, 11 (3) : 172-185.
  • 5Louis S L, Donald P, Xavier M. Real-time object detection and background maintenance for uncontrolled environments [ C]// Proceedings of the 5th International Conference on Signal Processing, Pattern Recognition, and Applications. Stevens Point, Wisconsin, USA: WSEAS, 2008: 599-604.
  • 6查成东,王长松,巩宪锋,周家新.基于自适应背景模型的运动目标检测[J].光电工程,2008,35(1):26-30. 被引量:6
  • 7张军,代科学,李国辉.基于HSV颜色空间和码本模型的运动目标检测[J].系统工程与电子技术,2008,30(3):423-427. 被引量:14
  • 8王永忠,梁彦,潘泉,程咏梅,赵春晖.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. 被引量:78

共引文献28

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部